{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:45:36Z","timestamp":1787017536337,"version":"build-2736575974"},"reference-count":188,"publisher":"Association for Computing Machinery (ACM)","issue":"1","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGKDD Explor. Newsl."],"published-print":{"date-parts":[[2026,6,17]]},"abstract":"<jats:p>Large language models (LLMs) and large vision-language models (LVLMs) have demonstrated impressive generative capabilities, yet ensuring their outputs align with user intent is still challenging. While most existing approaches address this issue at the training stage, inference-time approaches like decoding methods offer a more efficient and scalable solution. Decoding methods control model generation by guiding token-level selection, performing sequencelevel generation, or generating tokens in parallel to accelerate the process. In this survey, we identify three emerging paradigms from recent works on decoding methods for LLMs and LVLMs, provide a systematic review of these methods, highlight ongoing challenges, and discuss potential future research directions. Our goal is to underscore the efficiency and effectiveness of decoding methods and offer a practical view of their applications. Paper lists and more resources on decoding methods for LLMs and LVLMs can be found at https:\/\/github.com\/wang2226\/Awesome-LLM-Decoding.<\/jats:p>","DOI":"10.1145\/3820356.3820357","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T15:58:43Z","timestamp":1781711923000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Beyond Tokens: A Survey on Decoding Methods for Large Language and Vision-Language Models"],"prefix":"10.1145","volume":"28","author":[{"given":"Haoran","family":"Wang","sequence":"first","affiliation":[{"name":"Emory University, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiongxiao","family":"Xu","sequence":"additional","affiliation":[{"name":"Illinois Institute of Technology, Chicago, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip S.","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Illinois Chicago, Chicago, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Shu","sequence":"additional","affiliation":[{"name":"Emory University, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,17]]},"reference":[{"key":"e_1_2_1_1_1","first-page":"36","article-title":"Monitor-guided decoding of code lms with static analysis of repository context","author":"Agrawal L. A.","year":"2024","unstructured":"L. A. Agrawal, A. Kanade, N. Goyal, S. Lahiri, and S. Rajamani. Monitor-guided decoding of code lms with static analysis of repository context. Advances in Neural Information Processing Systems, 36, 2024.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_2_1","volume-title":"Safeinfer: Context adaptive decoding time safety alignment for large language models. arXiv preprint arXiv:2406.12274","author":"Banerjee S.","year":"2024","unstructured":"S. Banerjee, S. Tripathy, S. Layek, S. Kumar, A. Mukherjee, and R. Hazra. Safeinfer: Context adaptive decoding time safety alignment for large language models. arXiv preprint arXiv:2406.12274, 2024."},{"key":"e_1_2_1_3_1","volume-title":"Decoding matters: Addressing amplification bias and homogeneity issue for llm-based recommendation. arXiv preprint arXiv:2406.14900","author":"Bao K.","year":"2024","unstructured":"K. Bao, J. Zhang, Y. Zhang, X. Huo, C. Chen, and F. Feng. Decoding matters: Addressing amplification bias and homogeneity issue for llm-based recommendation. arXiv preprint arXiv:2406.14900, 2024."},{"key":"e_1_2_1_4_1","volume-title":"Eliciting latent predictions from transformers with the tuned lens. arXiv preprint arXiv:2303.08112","author":"Belrose N.","year":"2023","unstructured":"N. Belrose, Z. Furman, L. Smith, D. Halawi, I. Ostrovsky, L. McKinney, S. Biderman, and J. Steinhardt. Eliciting latent predictions from transformers with the tuned lens. arXiv preprint arXiv:2303.08112, 2023."},{"key":"e_1_2_1_5_1","volume-title":"Mechanistic interpretability for ai safety-a review. arXiv preprint arXiv:2404.14082","author":"Bereska L.","year":"2024","unstructured":"L. Bereska and E. Gavves. Mechanistic interpretability for ai safety-a review. arXiv preprint arXiv:2404.14082, 2024."},{"key":"e_1_2_1_6_1","volume-title":"Guiding llms the right way: Fast, non-invasive constrained generation. arXiv preprint arXiv:2403.06988","author":"Beurer-Kellner L.","year":"2024","unstructured":"L. Beurer-Kellner, M. Fischer, and M. Vechev. Guiding llms the right way: Fast, non-invasive constrained generation. arXiv preprint arXiv:2403.06988, 2024."},{"key":"e_1_2_1_7_1","volume-title":"Language models are few-shot learners. Advances in neural information processing systems, 33:1877-1901","author":"Brown T.","year":"2020","unstructured":"T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, et al. Language models are few-shot learners. Advances in neural information processing systems, 33:1877-1901, 2020."},{"key":"e_1_2_1_8_1","volume-title":"Medusa: Simple llm inference acceleration framework with multiple decoding heads. arXiv preprint arXiv:2401.10774","author":"Cai T.","year":"2024","unstructured":"T. Cai, Y. Li, Z. Geng, H. Peng, J. D. Lee, D. Chen, and T. Dao. Medusa: Simple llm inference acceleration framework with multiple decoding heads. arXiv preprint arXiv:2401.10774, 2024."},{"key":"e_1_2_1_9_1","volume-title":"Nothing in excess: Mitigating the exaggerated safety for llms via safety-conscious activation steering. arXiv preprint arXiv:2408.11491","author":"Cao Z.","year":"2024","unstructured":"Z. Cao, Y. Yang, and H. Zhao. Nothing in excess: Mitigating the exaggerated safety for llms via safety-conscious activation steering. arXiv preprint arXiv:2408.11491, 2024."},{"key":"e_1_2_1_10_1","volume-title":"Defending against unforeseen failure modes with latent adversarial training. arXiv preprint arXiv:2403.05030","author":"Casper S.","year":"2024","unstructured":"S. Casper, L. Schulze, O. Patel, and D. Hadfield- Menell. Defending against unforeseen failure modes with latent adversarial training. arXiv preprint arXiv:2403.05030, 2024."},{"key":"e_1_2_1_11_1","volume-title":"Transfer q star: Principled decoding for llm alignment. arXiv preprint arXiv:2405.20495","author":"Chakraborty S.","year":"2024","unstructured":"S. Chakraborty, S. S. Ghosal, M. Yin, D. Manocha, M. Wang, A. S. Bedi, and F. Huang. Transfer q star: Principled decoding for llm alignment. arXiv preprint arXiv:2405.20495, 2024."},{"key":"e_1_2_1_12_1","first-page":"14084","article-title":"Deep extrapolation for attribute-enhanced generation","volume":"34","author":"Chan A.","year":"2021","unstructured":"A. Chan, A. Madani, B. Krause, and N. Naik. Deep extrapolation for attribute-enhanced generation. Advances in Neural Information Processing Systems, 34:14084-14096, 2021.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_13_1","volume-title":"Explaining and improving contrastive decoding by extrapolating the probabilities of a huge and hypothetical lm. arXiv preprint arXiv:2411.01610","author":"Chang H.-S.","year":"2024","unstructured":"H.-S. Chang, N. Peng, M. Bansal, A. Ramakrishna, and T. Chung. Explaining and improving contrastive decoding by extrapolating the probabilities of a huge and hypothetical lm. arXiv preprint arXiv:2411.01610, 2024."},{"key":"e_1_2_1_14_1","volume-title":"Attention hijackers: Detect and disentangle attention hijacking in lvlms for hallucination mitigation. arXiv preprint arXiv:2503.08216","author":"Chen B.","year":"2025","unstructured":"B. Chen, X. Lyu, L. Gao, J. Song, and H. T. Shen. Attention hijackers: Detect and disentangle attention hijacking in lvlms for hallucination mitigation. arXiv preprint arXiv:2503.08216, 2025."},{"key":"e_1_2_1_15_1","volume-title":"Accelerating large language model decoding with speculative sampling. arXiv preprint arXiv:2302.01318","author":"Chen C.","year":"2023","unstructured":"C. Chen, S. Borgeaud, G. Irving, J.-B. Lespiau, L. Sifre, and J. Jumper. Accelerating large language model decoding with speculative sampling. arXiv preprint arXiv:2302.01318, 2023."},{"key":"e_1_2_1_16_1","doi-asserted-by":"crossref","first-page":"14162","DOI":"10.18653\/v1\/2024.findings-acl.842","volume-title":"Findings of the Association for Computational Linguistics ACL 2024","author":"Chen W.","year":"2024","unstructured":"W. Chen, W. Wang, Z. Chu, K. Ren, Z. Zheng, and Z. Lu. Self-para-consistency: Improving reasoning tasks at low cost for large language models. In Findings of the Association for Computational Linguistics ACL 2024, pages 14162-14167, 2024."},{"key":"e_1_2_1_17_1","volume-title":"Open-vocabulary auditory neural decoding using fmriprompted llm. arXiv preprint arXiv:2405.07840","author":"Chen X.","year":"2024","unstructured":"X. Chen, C. Du, C. Liu, Y. Wang, and H. He. Open-vocabulary auditory neural decoding using fmriprompted llm. arXiv preprint arXiv:2405.07840, 2024."},{"key":"e_1_2_1_18_1","volume-title":"Black-box prompt optimization: Aligning large language models without model training. arXiv preprint arXiv:2311.04155","author":"Cheng J.","year":"2023","unstructured":"J. Cheng, X. Liu, K. Zheng, P. Ke, H. Wang, Y. Dong, J. Tang, and M. Huang. Black-box prompt optimization: Aligning large language models without model training. arXiv preprint arXiv:2311.04155, 2023."},{"key":"e_1_2_1_19_1","volume-title":"Integrative decoding: Improve factuality via implicit selfconsistency. arXiv preprint arXiv:2410.01556","author":"Cheng Y.","year":"2024","unstructured":"Y. Cheng, X. Liang, Y. Gong, W. Xiao, S. Wang, Y. Zhang, W. Hou, K. Xu, W. Liu, W. Li, et al. Integrative decoding: Improve factuality via implicit selfconsistency. arXiv preprint arXiv:2410.01556, 2024."},{"key":"e_1_2_1_20_1","volume-title":"Dola: Decoding by contrasting layers improves factuality in large language models. arXiv preprint arXiv:2309.03883","author":"Chuang Y.-S.","year":"2023","unstructured":"Y.-S. Chuang, Y. Xie, H. Luo, Y. Kim, J. Glass, and P. He. Dola: Decoding by contrasting layers improves factuality in large language models. arXiv preprint arXiv:2309.03883, 2023."},{"key":"e_1_2_1_21_1","volume-title":"Knowledge neurons in pretrained transformers. arXiv preprint arXiv:2104.08696","author":"Dai D.","year":"2021","unstructured":"D. Dai, L. Dong, Y. Hao, Z. Sui, B. Chang, and F.Wei. Knowledge neurons in pretrained transformers. arXiv preprint arXiv:2104.08696, 2021."},{"key":"e_1_2_1_22_1","volume-title":"Safe rlhf: Safe reinforcement learning from human feedback. arXiv preprint arXiv:2310.12773","author":"Dai J.","year":"2023","unstructured":"J. Dai, X. Pan, R. Sun, J. Ji, X. Xu, M. Liu, Y. Wang, and Y. Yang. Safe rlhf: Safe reinforcement learning from human feedback. arXiv preprint arXiv:2310.12773, 2023."},{"key":"e_1_2_1_23_1","volume-title":"Entropy guided extrapolative decoding to improve factuality in large language models. arXiv preprint arXiv:2404.09338","author":"Das S.","year":"2024","unstructured":"S. Das, L. Jin, L. Song, H. Mi, B. Peng, and D. Yu. Entropy guided extrapolative decoding to improve factuality in large language models. arXiv preprint arXiv:2404.09338, 2024."},{"key":"e_1_2_1_24_1","volume-title":"Plug and play language models: A simple approach to controlled text generation. arXiv preprint arXiv:1912.02164","author":"Dathathri S.","year":"2019","unstructured":"S. Dathathri, A. Madotto, J. Lan, J. Hung, E. Frank, P. Molino, J. Yosinski, and R. Liu. Plug and play language models: A simple approach to controlled text generation. arXiv preprint arXiv:1912.02164, 2019."},{"key":"e_1_2_1_25_1","volume-title":"Seeing is believing: Mitigating hallucination in large visionlanguage models via clip-guided decoding. arXiv preprint arXiv:2402.15300","author":"Deng A.","year":"2024","unstructured":"A. Deng, Z. Chen, and B. Hooi. Seeing is believing: Mitigating hallucination in large visionlanguage models via clip-guided decoding. arXiv preprint arXiv:2402.15300, 2024."},{"key":"e_1_2_1_26_1","volume-title":"Reward-augmented decoding: Efficient controlled text generation with a unidirectional reward model. arXiv preprint arXiv:2310.09520","author":"Deng H.","year":"2023","unstructured":"H. Deng and C. Raffel. Reward-augmented decoding: Efficient controlled text generation with a unidirectional reward model. arXiv preprint arXiv:2310.09520, 2023."},{"key":"e_1_2_1_27_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin J.","year":"2018","unstructured":"J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018."},{"key":"e_1_2_1_28_1","volume-title":"Adaptive decoding via latent preference optimization. arXiv preprint arXiv:2411.09661","author":"Dhuliawala S.","year":"2024","unstructured":"S. Dhuliawala, I. Kulikov, P. Yu, A. Celikyilmaz, J. Weston, S. Sukhbaatar, and J. Lanchantin. Adaptive decoding via latent preference optimization. arXiv preprint arXiv:2411.09661, 2024."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3554727"},{"key":"e_1_2_1_30_1","volume-title":"Unified language model pre-training for natural language understanding and generation. Advances in neural information processing systems, 32","author":"Dong L.","year":"2019","unstructured":"L. Dong, N. Yang, W.Wang, F.Wei, X. Liu, Y.Wang, J. Gao, M. Zhou, and H.-W. Hon. Unified language model pre-training for natural language understanding and generation. Advances in neural information processing systems, 32, 2019."},{"key":"e_1_2_1_31_1","volume-title":"Hierarchical neural story generation. arXiv preprint arXiv:1805.04833","author":"Fan A.","year":"2018","unstructured":"A. Fan, M. Lewis, and Y. Dauphin. Hierarchical neural story generation. arXiv preprint arXiv:1805.04833, 2018."},{"key":"e_1_2_1_32_1","volume-title":"Position-aware depth decay decoding: Boosting large language model inference efficiency. arXiv preprint arXiv:2503.08524","author":"Fan S.","year":"2025","unstructured":"S. Fan, X. Fang, X. Xing, P. Han, S. Shang, and Y. Wang. Position-aware depth decay decoding: Boosting large language model inference efficiency. arXiv preprint arXiv:2503.08524, 2025."},{"key":"e_1_2_1_33_1","volume-title":"From uncertainty to trust: Enhancing reliability in visionlanguage models with uncertainty-guided dropout decoding. arXiv preprint arXiv:2412.06474","author":"Fang Y.","year":"2024","unstructured":"Y. Fang, Z. Yang, Z. Chen, Z. Zhao, and J. Zhou. From uncertainty to trust: Enhancing reliability in visionlanguage models with uncertainty-guided dropout decoding. arXiv preprint arXiv:2412.06474, 2024."},{"key":"e_1_2_1_34_1","volume-title":"Alphazero-like tree-search can guide large language model decoding and training. arXiv preprint arXiv:2309.17179","author":"Feng X.","year":"2023","unstructured":"X. Feng, Z. Wan, M. Wen, S. M. McAleer, Y. Wen, W. Zhang, and J. Wang. Alphazero-like tree-search can guide large language model decoding and training. arXiv preprint arXiv:2309.17179, 2023."},{"key":"e_1_2_1_35_1","volume-title":"Emage: Non-autoregressive text-to-image generation. arXiv preprint arXiv:2312.14988","author":"Feng Z.","year":"2023","unstructured":"Z. Feng, R. Hu, L. Liu, F. Zhang, D. Tang, Y. Dai, X. Feng, J. Li, B. Qin, and S. Shi. Emage: Non-autoregressive text-to-image generation. arXiv preprint arXiv:2312.14988, 2023."},{"key":"e_1_2_1_36_1","volume-title":"Break the sequential dependency of llm inference using lookahead decoding. arXiv preprint arXiv:2402.02057","author":"Fu Y.","year":"2024","unstructured":"Y. Fu, P. Bailis, I. Stoica, and H. Zhang. Break the sequential dependency of llm inference using lookahead decoding. arXiv preprint arXiv:2402.02057, 2024."},{"key":"e_1_2_1_37_1","volume-title":"Constrained decoding for secure code generation. arXiv preprint arXiv:2405.00218","author":"Fu Y.","year":"2024","unstructured":"Y. Fu, E. Baker, Y. Ding, and Y. Chen. Constrained decoding for secure code generation. arXiv preprint arXiv:2405.00218, 2024."},{"key":"e_1_2_1_38_1","volume-title":"Impact of decoding methods on human alignment of conversational llms. arXiv preprint arXiv:2407.19526","author":"Furniturewala S.","year":"2024","unstructured":"S. Furniturewala, K. Jaidka, and Y. Sharma. Impact of decoding methods on human alignment of conversational llms. arXiv preprint arXiv:2407.19526, 2024."},{"key":"e_1_2_1_39_1","volume-title":"On speculative decoding for multimodal large language models. arXiv preprint arXiv:2404.08856","author":"Gagrani M.","year":"2024","unstructured":"M. Gagrani, R. Goel, W. Jeon, J. Park, M. Lee, and C. Lott. On speculative decoding for multimodal large language models. arXiv preprint arXiv:2404.08856, 2024."},{"key":"e_1_2_1_40_1","volume-title":"Decore: Decoding by contrasting retrieval heads to mitigate hallucinations. arXiv preprint arXiv:2410.18860","author":"Gema A. P.","year":"2024","unstructured":"A. P. Gema, C. Jin, A. Abdulaal, T. Diethe, P. Teare, B. Alex, P. Minervini, and A. Saseendran. Decore: Decoding by contrasting retrieval heads to mitigate hallucinations. arXiv preprint arXiv:2410.18860, 2024."},{"key":"e_1_2_1_41_1","volume-title":"Critic: Large language models can selfcorrect with tool-interactive critiquing. arXiv preprint arXiv:2305.11738","author":"Gou Z.","year":"2023","unstructured":"Z. Gou, Z. Shao, Y. Gong, Y. Shen, Y. Yang, N. Duan, and W. Chen. Critic: Large language models can selfcorrect with tool-interactive critiquing. arXiv preprint arXiv:2305.11738, 2023."},{"key":"e_1_2_1_42_1","volume-title":"Rest: Retrieval-based speculative decoding. arXiv preprint arXiv:2311.08252","author":"He Z.","year":"2023","unstructured":"Z. He, Z. Zhong, T. Cai, J. D. Lee, and D. He. Rest: Retrieval-based speculative decoding. arXiv preprint arXiv:2311.08252, 2023."},{"key":"e_1_2_1_43_1","volume-title":"The curious case of neural text degeneration. arXiv preprint arXiv:1904.09751","author":"Holtzman A.","year":"2019","unstructured":"A. Holtzman, J. Buys, L. Du, M. Forbes, and Y. Choi. The curious case of neural text degeneration. arXiv preprint arXiv:1904.09751, 2019."},{"key":"e_1_2_1_44_1","volume-title":"Learning to write with cooperative discriminators. arXiv preprint arXiv:1805.06087","author":"Holtzman A.","year":"2018","unstructured":"A. Holtzman, J. Buys, M. Forbes, A. Bosselut, D. Golub, and Y. Choi. Learning to write with cooperative discriminators. arXiv preprint arXiv:1805.06087, 2018."},{"key":"e_1_2_1_45_1","volume-title":"Towards reasoning in large language models: A survey. arXiv preprint arXiv:2212.10403","author":"Huang J.","year":"2022","unstructured":"J. Huang and K. C.-C. Chang. Towards reasoning in large language models: A survey. arXiv preprint arXiv:2212.10403, 2022."},{"key":"e_1_2_1_46_1","volume-title":"ACM Transactions on Information Systems","author":"Huang L.","year":"2023","unstructured":"L. Huang, W. Yu, W. Ma, W. Zhong, Z. Feng, H. Wang, Q. Chen, W. Peng, X. Feng, B. Qin, et al. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. ACM Transactions on Information Systems, 2023."},{"key":"e_1_2_1_47_1","first-page":"36","article-title":"Grounded decoding: Guiding text generation with grounded models for embodied agents","author":"Huang W.","year":"2024","unstructured":"W. Huang, F. Xia, D. Shah, D. Driess, A. Zeng, Y. Lu, P. Florence, I. Mordatch, S. Levine, K. Hausman, et al. Grounded decoding: Guiding text generation with grounded models for embodied agents. Advances in Neural Information Processing Systems, 36, 2024.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_48_1","volume-title":"Self-introspective decoding: Alleviating hallucinations for large vision-language models. arXiv preprint arXiv:2408.02032","author":"Huo F.","year":"2024","unstructured":"F. Huo, W. Xu, Z. Zhang, H. Wang, Z. Chen, and P. Zhao. Self-introspective decoding: Alleviating hallucinations for large vision-language models. arXiv preprint arXiv:2408.02032, 2024."},{"key":"e_1_2_1_49_1","volume-title":"Lantern: Accelerating visual autoregressive models with relaxed speculative decoding. arXiv preprint arXiv:2410.03355","author":"Jang D.","year":"2024","unstructured":"D. Jang, S. Park, J. Y. Yang, Y. Jung, J. Yun, S. Kundu, S.-Y. Kim, and E. Yang. Lantern: Accelerating visual autoregressive models with relaxed speculative decoding. arXiv preprint arXiv:2410.03355, 2024."},{"key":"e_1_2_1_50_1","volume-title":"A data-driven guided decoding mechanism for diagnostic captioning. arXiv preprint arXiv:2406.14164","author":"Kaliosis P.","year":"2024","unstructured":"P. Kaliosis, J. Pavlopoulos, F. Charalampakos, G. Moschovis, and I. Androutsopoulos. A data-driven guided decoding mechanism for diagnostic captioning. arXiv preprint arXiv:2406.14164, 2024."},{"key":"e_1_2_1_51_1","volume-title":"Catch: Complementary adaptive token-level contrastive decoding to mitigate hallucinations in lvlms. arXiv preprint arXiv:2411.12713","author":"Kan Z.","year":"2024","unstructured":"Z. Kan, C. Zhang, Z. Liao, Y. Tian, W. Yang, J. Xiao, X. Li, D. Jiang, Y. Wang, and Q. Liao. Catch: Complementary adaptive token-level contrastive decoding to mitigate hallucinations in lvlms. arXiv preprint arXiv:2411.12713, 2024."},{"key":"e_1_2_1_52_1","volume-title":"A distributional approach to controlled text generation. arXiv preprint arXiv:2012.11635","author":"Khalifa M.","year":"2020","unstructured":"M. Khalifa, H. Elsahar, and M. Dymetman. A distributional approach to controlled text generation. arXiv preprint arXiv:2012.11635, 2020."},{"key":"e_1_2_1_53_1","volume-title":"Critic-guided decoding for controlled text generation. arXiv preprint arXiv:2212.10938","author":"Kim M.","year":"2022","unstructured":"M. Kim, H. Lee, K. M. Yoo, J. Park, H. Lee, and K. Jung. Critic-guided decoding for controlled text generation. arXiv preprint arXiv:2212.10938, 2022."},{"key":"e_1_2_1_54_1","volume-title":"Vacode: Visual augmented contrastive decoding. arXiv preprint arXiv:2408.05337","author":"Kim S.","year":"2024","unstructured":"S. Kim, B. Cho, S. Bae, S. Ahn, and S.-Y. Yun. Vacode: Visual augmented contrastive decoding. arXiv preprint arXiv:2408.05337, 2024."},{"key":"e_1_2_1_55_1","volume-title":"Adaptive contrastive decoding in retrieval-augmented generation for handling noisy contexts. arXiv preprint arXiv:2408.01084","author":"Kim Y.","year":"2024","unstructured":"Y. Kim, H. J. Kim, C. Park, C. Park, H. Cho, J. Kim, K. M. Yoo, S.-g. Lee, and T. Kim. Adaptive contrastive decoding in retrieval-augmented generation for handling noisy contexts. arXiv preprint arXiv:2408.01084, 2024."},{"key":"e_1_2_1_56_1","volume-title":"Style vectors for steering generative large language model. arXiv preprint arXiv:2402.01618","author":"Konen K.","year":"2024","unstructured":"K. Konen, S. Jentzsch, D. Diallo, P. Sch\u00a8utt, O. Bensch, R. E. Baff, D. Opitz, and T. Hecking. Style vectors for steering generative large language model. arXiv preprint arXiv:2402.01618, 2024."},{"key":"e_1_2_1_57_1","volume-title":"Nonparametric decoding for generative retrieval. arXiv preprint arXiv:2210.02068","author":"Lee H.","year":"2022","unstructured":"H. Lee, J. Kim, H. Chang, H. Oh, S. Yang, V. Karpukhin, Y. Lu, and M. Seo. Nonparametric decoding for generative retrieval. arXiv preprint arXiv:2210.02068, 2022."},{"key":"e_1_2_1_58_1","volume-title":"Delve into visual contrastive decoding for hallucination mitigation of large vision-language models. arXiv preprint arXiv:2412.06775","author":"Lee Y.-L.","year":"2024","unstructured":"Y.-L. Lee, Y.-H. Tsai, and W.-C. Chiu. Delve into visual contrastive decoding for hallucination mitigation of large vision-language models. arXiv preprint arXiv:2412.06775, 2024."},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"e_1_2_1_60_1","volume-title":"The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691","author":"Lester B.","year":"2021","unstructured":"B. Lester, R. Al-Rfou, and N. Constant. The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691, 2021."},{"key":"e_1_2_1_61_1","first-page":"19274","volume-title":"International Conference on Machine Learning","author":"Leviathan Y.","year":"2023","unstructured":"Y. Leviathan, M. Kalman, and Y. Matias. Fast inference from transformers via speculative decoding. In International Conference on Machine Learning, pages 19274-19286. PMLR, 2023."},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"e_1_2_1_63_1","volume-title":"Doce: Finding the sweet spot for execution-based code generation. arXiv preprint arXiv:2408.13745","author":"Li H.-S.","year":"2024","unstructured":"H.-S. Li, P. Fernandes, I. Gurevych, and A. F. Martins. Doce: Finding the sweet spot for execution-based code generation. arXiv preprint arXiv:2408.13745, 2024."},{"key":"e_1_2_1_64_1","first-page":"36","article-title":"Inference-time intervention: Eliciting truthful answers from a language model","author":"Li K.","year":"2024","unstructured":"K. Li, O. Patel, F. Vi\u00b4egas, H. Pfister, and M. Wattenberg. Inference-time intervention: Eliciting truthful answers from a language model. Advances in Neural Information Processing Systems, 36, 2024.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_65_1","volume-title":"Videogen: A reference-guided latent diffusion approach for high definition text-to-video generation. arXiv preprint arXiv:2309.00398","author":"Li X.","year":"2023","unstructured":"X. Li, W. Chu, Y. Wu, W. Yuan, F. Liu, Q. Zhang, F. Li, H. Feng, E. Ding, and J. Wang. Videogen: A reference-guided latent diffusion approach for high definition text-to-video generation. arXiv preprint arXiv:2309.00398, 2023."},{"key":"e_1_2_1_66_1","volume-title":"Contrastive decoding: Open-ended text generation as optimization. arXiv preprint arXiv:2210.15097","author":"Li X. L.","year":"2022","unstructured":"X. L. Li, A. Holtzman, D. Fried, P. Liang, J. Eisner, T. Hashimoto, L. Zettlemoyer, and M. Lewis. Contrastive decoding: Open-ended text generation as optimization. arXiv preprint arXiv:2210.15097, 2022."},{"key":"e_1_2_1_67_1","volume-title":"Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190","author":"Li X. L.","year":"2021","unstructured":"X. L. Li and P. Liang. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190, 2021."},{"key":"e_1_2_1_68_1","volume-title":"Eagle-2: Faster inference of language models with dynamic draft trees. arXiv preprint arXiv:2406.16858","author":"Li Y.","year":"2024","unstructured":"Y. Li, F.Wei, C. Zhang, and H. Zhang. Eagle-2: Faster inference of language models with dynamic draft trees. arXiv preprint arXiv:2406.16858, 2024."},{"key":"e_1_2_1_69_1","volume-title":"Eagle: Speculative sampling requires rethinking feature uncertainty. arXiv preprint arXiv:2401.15077","author":"Li Y.","year":"2024","unstructured":"Y. Li, F. Wei, C. Zhang, and H. Zhang. Eagle: Speculative sampling requires rethinking feature uncertainty. arXiv preprint arXiv:2401.15077, 2024."},{"key":"e_1_2_1_70_1","volume-title":"Controllable text generation for large language models: A survey. arXiv preprint arXiv:2408.12599","author":"Liang X.","year":"2024","unstructured":"X. Liang, H.Wang, Y.Wang, S. Song, J. Yang, S. Niu, J. Hu, D. Liu, S. Yao, F. Xiong, and Z. Li. Controllable text generation for large language models: A survey. arXiv preprint arXiv:2408.12599, 2024."},{"key":"e_1_2_1_71_1","volume-title":"A survey on mechanistic interpretability for multi-modal foundation models. arXiv preprint arXiv:2502.17516","author":"Lin Z.","year":"2025","unstructured":"Z. Lin, S. Basu, M. Beigi, V. Manjunatha, R. A. Rossi, Z. Wang, Y. Zhou, S. Balasubramanian, A. Zarei, K. Rezaei, et al. A survey on mechanistic interpretability for multi-modal foundation models. arXiv preprint arXiv:2502.17516, 2025."},{"key":"e_1_2_1_72_1","volume-title":"Direct large language model alignment through self-rewarding contrastive prompt distillation. arXiv preprint arXiv:2402.11907","author":"Liu A.","year":"2024","unstructured":"A. Liu, H. Bai, Z. Lu, X. Kong, S. Wang, J. Shan, M. Cao, and L. Wen. Direct large language model alignment through self-rewarding contrastive prompt distillation. arXiv preprint arXiv:2402.11907, 2024."},{"key":"e_1_2_1_73_1","volume-title":"Dexperts: Decodingtime controlled text generation with experts and antiexperts. arXiv preprint arXiv:2105.03023","author":"Liu A.","year":"2021","unstructured":"A. Liu, M. Sap, X. Lu, S. Swayamdipta, C. Bhagavatula, N. A. Smith, and Y. Choi. Dexperts: Decodingtime controlled text generation with experts and antiexperts. arXiv preprint arXiv:2105.03023, 2021."},{"key":"e_1_2_1_74_1","volume-title":"Making ppo even better: Value-guided monte-carlo tree search decoding. arXiv preprint arXiv:2309.15028","author":"Liu J.","year":"2023","unstructured":"J. Liu, A. Cohen, R. Pasunuru, Y. Choi, H. Hajishirzi, and A. Celikyilmaz. Making ppo even better: Value-guided monte-carlo tree search decoding. arXiv preprint arXiv:2309.15028, 2023."},{"key":"e_1_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_2_1_76_1","volume-title":"In-context vectors: Making in context learning more effective and controllable through latent space steering. arXiv preprint arXiv:2311.06668","author":"Liu S.","year":"2023","unstructured":"S. Liu, H. Ye, L. Xing, and J. Zou. In-context vectors: Making in context learning more effective and controllable through latent space steering. arXiv preprint arXiv:2311.06668, 2023."},{"key":"e_1_2_1_77_1","volume-title":"Expediting and elevating large language model reasoning via hidden chain-of-thought decoding. arXiv preprint arXiv:2409.08561","author":"Liu T.","year":"2024","unstructured":"T. Liu, Z. Chen, Z. Liu, M. Tian, and W. Luo. Expediting and elevating large language model reasoning via hidden chain-of-thought decoding. arXiv preprint arXiv:2409.08561, 2024."},{"key":"e_1_2_1_78_1","volume-title":"Online speculative decoding. arXiv preprint arXiv:2310.07177","author":"Liu X.","year":"2023","unstructured":"X. Liu, L. Hu, P. Bailis, A. Cheung, Z. Deng, I. Stoica, and H. Zhang. Online speculative decoding. arXiv preprint arXiv:2310.07177, 2023."},{"key":"e_1_2_1_79_1","volume-title":"Adaptive draftverification for efficient large language model decoding. arXiv preprint arXiv:2407.12021","author":"Liu X.","year":"2024","unstructured":"X. Liu, B. Lei, R. Zhang, and D. Xu. Adaptive draftverification for efficient large language model decoding. arXiv preprint arXiv:2407.12021, 2024."},{"key":"e_1_2_1_80_1","volume-title":"Bidirectional decoding: Improving action chunking via closed-loop resampling. arXiv preprint arXiv:2408.17355","author":"Liu Y.","year":"2024","unstructured":"Y. Liu, J. I. Hamid, A. Xie, Y. Lee, M. Du, and C. Finn. Bidirectional decoding: Improving action chunking via closed-loop resampling. arXiv preprint arXiv:2408.17355, 2024."},{"key":"e_1_2_1_81_1","volume-title":"Neurologic a* esque decoding: Constrained text generation with lookahead heuristics. arXiv preprint arXiv:2112.08726","author":"Lu X.","year":"2021","unstructured":"X. Lu, S. Welleck, P. West, L. Jiang, J. Kasai, D. Khashabi, R. L. Bras, L. Qin, Y. Yu, R. Zellers, et al. Neurologic a* esque decoding: Constrained text generation with lookahead heuristics. arXiv preprint arXiv:2112.08726, 2021."},{"key":"e_1_2_1_82_1","volume-title":"Neurologic decoding:(un) supervised neural text generation with predicate logic constraints. arXiv preprint arXiv:2010.12884","author":"Lu X.","year":"2020","unstructured":"X. Lu, P. West, R. Zellers, R. L. Bras, C. Bhagavatula, and Y. Choi. Neurologic decoding:(un) supervised neural text generation with predicate logic constraints. arXiv preprint arXiv:2010.12884, 2020."},{"key":"e_1_2_1_83_1","volume-title":"Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity. arXiv preprint arXiv:2104.08786","author":"Lu Y.","year":"2021","unstructured":"Y. Lu, M. Bartolo, A. Moore, S. Riedel, and P. Stenetorp. Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity. arXiv preprint arXiv:2104.08786, 2021."},{"key":"e_1_2_1_84_1","volume-title":"Odysseus navigates the sirens","author":"Luo W.","year":"2025","unstructured":"W. Luo, F. Song, W. Li, G. Peng, S. Wei, and H. Wang. Odysseus navigates the sirens\u2019 song: Dynamic focus decoding for factual and diverse open-ended text generation. arXiv preprint arXiv:2503.08057, 2025."},{"key":"e_1_2_1_85_1","first-page":"17359","article-title":"Locating and editing factual associations in gpt","volume":"35","author":"Meng K.","year":"2022","unstructured":"K. Meng, D. Bau, A. Andonian, and Y. Belinkov. Locating and editing factual associations in gpt. Advances in Neural Information Processing Systems, 35:17359-17372, 2022.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_86_1","volume-title":"Mass-editing memory in a transformer. arXiv preprint arXiv:2210.07229","author":"Meng K.","year":"2022","unstructured":"K. Meng, A. S. Sharma, A. Andonian, Y. Belinkov, and D. Bau. Mass-editing memory in a transformer. arXiv preprint arXiv:2210.07229, 2022."},{"key":"e_1_2_1_87_1","first-page":"12","article-title":"Our most capable models to date","author":"Meta A.","year":"2024","unstructured":"A. Meta. Introducing llama 3.1: Our most capable models to date. Meta AI Blog, 12, 2024.","journal-title":"Meta AI Blog"},{"key":"e_1_2_1_88_1","volume-title":"et al. Specinfer: Accelerating generative large language model serving with tree-based speculative inference and verification. arXiv preprint arXiv:2305.09781","author":"Miao X.","year":"2023","unstructured":"X. Miao, G. Oliaro, Z. Zhang, X. Cheng, Z. Wang, Z. Zhang, R. Y. Y. Wong, A. Zhu, L. Yang, X. Shi, et al. Specinfer: Accelerating generative large language model serving with tree-based speculative inference and verification. arXiv preprint arXiv:2305.09781, 2023."},{"key":"e_1_2_1_89_1","volume-title":"Mitigating hallucinations in large vision-language models via summary-guided decoding. arXiv preprint arXiv:2410.13321","author":"Min K.","year":"2024","unstructured":"K. Min, M. Kim, K.-i. Lee, D. Lee, and K. Jung. Mitigating hallucinations in large vision-language models via summary-guided decoding. arXiv preprint arXiv:2410.13321, 2024."},{"key":"e_1_2_1_90_1","volume-title":"Correcting length bias in neural machine translation. arXiv preprint arXiv:1808.10006","author":"Murray K.","year":"2018","unstructured":"K. Murray and D. Chiang. Correcting length bias in neural machine translation. arXiv preprint arXiv:1808.10006, 2018."},{"key":"e_1_2_1_91_1","doi-asserted-by":"crossref","first-page":"1835","DOI":"10.1145\/3576915.3616652","volume-title":"Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security","author":"Naseh A.","year":"2023","unstructured":"A. Naseh, K. Krishna, M. Iyyer, and A. Houmansadr. Stealing the decoding algorithms of language models. In Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, pages 1835-1849, 2023."},{"key":"e_1_2_1_92_1","first-page":"26106","volume-title":"International Conference on Machine Learning","author":"Ni A.","year":"2023","unstructured":"A. Ni, S. Iyer, D. Radev, V. Stoyanov, W.-t. Yih, S. Wang, and X. V. Lin. Lever: Learning to verify language-to-code generation with execution. In International Conference on Machine Learning, pages 26106-26128. PMLR, 2023."},{"key":"e_1_2_1_93_1","volume-title":"Decoding secret memorization in code llms through token-level characterization. arXiv preprint arXiv:2410.08858","author":"Nie Y.","year":"2024","unstructured":"Y. Nie, C. Wang, K. Wang, G. Xu, G. Xu, and H. Wang. Decoding secret memorization in code llms through token-level characterization. arXiv preprint arXiv:2410.08858, 2024."},{"key":"e_1_2_1_94_1","volume-title":"Parameterefficient detoxification with contrastive decoding. arXiv preprint arXiv:2401.06947","author":"Niu T.","year":"2024","unstructured":"T. Niu, C. Xiong, S. Yavuz, and Y. Zhou. Parameterefficient detoxification with contrastive decoding. arXiv preprint arXiv:2401.06947, 2024."},{"key":"e_1_2_1_95_1","volume-title":"Contrastive decoding improves reasoning in large language models. arXiv preprint arXiv:2309.09117","author":"O\u2019Brien S.","year":"2023","unstructured":"S. O\u2019Brien and M. Lewis. Contrastive decoding improves reasoning in large language models. arXiv preprint arXiv:2309.09117, 2023."},{"key":"e_1_2_1_96_1","volume-title":"Training language models to follow instructions with human feedback. Advances in neural information processing systems, 35:27730-27744","author":"Ouyang L.","year":"2022","unstructured":"L. Ouyang, J. Wu, X. Jiang, D. Almeida, C. Wainwright, P. Mishkin, C. Zhang, S. Agarwal, K. Slama, A. Ray, et al. Training language models to follow instructions with human feedback. Advances in neural information processing systems, 35:27730-27744, 2022."},{"key":"e_1_2_1_97_1","volume-title":"Future lens: Anticipating subsequent tokens from a single hidden state. arXiv preprint arXiv:2311.04897","author":"Pal K.","year":"2023","unstructured":"K. Pal, J. Sun, A. Yuan, B. C. Wallace, and D. Bau. Future lens: Anticipating subsequent tokens from a single hidden state. arXiv preprint arXiv:2311.04897, 2023."},{"key":"e_1_2_1_98_1","volume-title":"Convis: Contrastive decoding with hallucination visualization for mitigating hallucinations in multimodal large language models. arXiv preprint arXiv:2408.13906","author":"Park Y.","year":"2024","unstructured":"Y. Park, D. Lee, J. Choe, and B. Chang. Convis: Contrastive decoding with hallucination visualization for mitigating hallucinations in multimodal large language models. arXiv preprint arXiv:2408.13906, 2024."},{"key":"e_1_2_1_99_1","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Peters M. E.","year":"2018","unstructured":"M. E. Peters, M. Neumann, M. Iyyer, M. Gardner, C. Clark, K. Lee, and L. Zettlemoyer. Deep contextualized word representations. In M. Walker, H. Ji, and A. Stent, editors, Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 2227- 2237, New Orleans, Louisiana, June 2018. Association for Computational Linguistics."},{"key":"e_1_2_1_100_1","volume-title":"The era of semantic decoding. arXiv preprint arXiv:2403.14562","author":"Peyrard M.","year":"2024","unstructured":"M. Peyrard, M. Josifoski, and R. West. The era of semantic decoding. arXiv preprint arXiv:2403.14562, 2024."},{"key":"e_1_2_1_101_1","volume-title":"Distillation contrastive decoding: Improving llms reasoning with contrastive decoding and distillation. arXiv preprint arXiv:2402.14874","author":"Phan P.","year":"2024","unstructured":"P. Phan, H. Tran, and L. Phan. Distillation contrastive decoding: Improving llms reasoning with contrastive decoding and distillation. arXiv preprint arXiv:2402.14874, 2024."},{"key":"e_1_2_1_102_1","volume-title":"Doccgen: Document-based controlled code generation. arXiv preprint arXiv:2406.11925","author":"Pimparkhede S.","year":"2024","unstructured":"S. Pimparkhede, M. Kammakomati, S. Tamilselvam, P. Kumar, A. P. Kumar, and P. Bhattacharyya. Doccgen: Document-based controlled code generation. arXiv preprint arXiv:2406.11925, 2024."},{"key":"e_1_2_1_103_1","volume-title":"Towards tracing trustworthiness dynamics: Revisiting pre-training period of large language models. arXiv preprint arXiv:2402.19465","author":"Qian C.","year":"2024","unstructured":"C. Qian, J. Zhang, W. Yao, D. Liu, Z. Yin, Y. Qiao, Y. Liu, and J. Shao. Towards tracing trustworthiness dynamics: Revisiting pre-training period of large language models. arXiv preprint arXiv:2402.19465, 2024."},{"key":"e_1_2_1_104_1","volume-title":"Entropy-based decoding for retrieval-augmented large language models. arXiv preprint arXiv:2406.17519","author":"Qiu Z.","year":"2024","unstructured":"Z. Qiu, Z. Ou, B. Wu, J. Li, A. Liu, and I. King. Entropy-based decoding for retrieval-augmented large language models. arXiv preprint arXiv:2406.17519, 2024."},{"key":"e_1_2_1_105_1","volume-title":"Improving language understanding with unsupervised learning","author":"Radford A.","year":"2018","unstructured":"A. Radford, K. Narasimhan, T. Salimans, and I. Sutskever. Improving language understanding with unsupervised learning, 2018."},{"issue":"8","key":"e_1_2_1_106_1","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford A.","year":"2019","unstructured":"A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, I. Sutskever, et al. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9, 2019.","journal-title":"OpenAI blog"},{"key":"e_1_2_1_107_1","volume-title":"Exploring the limits of transfer learning with a unified textto- text transformer. Journal of machine learning research, 21(140):1-67","author":"Raffel C.","year":"2020","unstructured":"C. Raffel, N. Shazeer, A. Roberts, K. Lee, S. Narang, M. Matena, Y. Zhou, W. Li, and P. J. Liu. Exploring the limits of transfer learning with a unified textto- text transformer. Journal of machine learning research, 21(140):1-67, 2020."},{"key":"e_1_2_1_108_1","volume-title":"Accelerating transformer inference for translation via parallel decoding. arXiv preprint arXiv:2305.10427","author":"Santilli A.","year":"2023","unstructured":"A. Santilli, S. Severino, E. Postolache, V. Maiorca, M. Mancusi, R. Marin, and E. Rodol'a. Accelerating transformer inference for translation via parallel decoding. arXiv preprint arXiv:2305.10427, 2023."},{"key":"e_1_2_1_109_1","volume-title":"Quantifying language models","author":"Sclar M.","year":"2023","unstructured":"M. Sclar, Y. Choi, Y. Tsvetkov, and A. Suhr. Quantifying language models\u2019 sensitivity to spurious features in prompt design or: How i learned to start worrying about prompt formatting. arXiv preprint arXiv:2310.11324, 2023."},{"key":"e_1_2_1_110_1","volume-title":"Towards understanding sycophancy in language models. arXiv preprint arXiv:2310.13548","author":"Sharma M.","year":"2023","unstructured":"M. Sharma, M. Tong, T. Korbak, D. Duvenaud, A. Askell, S. R. Bowman, N. Cheng, E. Durmus, Z. Hatfield-Dodds, S. R. Johnston, et al. Towards understanding sycophancy in language models. arXiv preprint arXiv:2310.13548, 2023."},{"key":"e_1_2_1_111_1","volume-title":"Superposed decoding: Multiple generations from a single autoregressive inference pass. arXiv preprint arXiv:2405.18400","author":"Shen E.","year":"2024","unstructured":"E. Shen, A. Fan, S. M. Pratt, J. S. Park, M. Wallingford, S. M. Kakade, A. Holtzman, R. Krishna, A. Farhadi, and A. Kusupati. Superposed decoding: Multiple generations from a single autoregressive inference pass. arXiv preprint arXiv:2405.18400, 2024."},{"key":"e_1_2_1_112_1","volume-title":"Learning to decode collaboratively with multiple language models. arXiv preprint arXiv:2403.03870","author":"Shen S. Z.","year":"2024","unstructured":"S. Z. Shen, H. Lang, B. Wang, Y. Kim, and D. Sontag. Learning to decode collaboratively with multiple language models. arXiv preprint arXiv:2403.03870, 2024."},{"key":"e_1_2_1_113_1","volume-title":"Large language model alignment: A survey. arXiv preprint arXiv:2309.15025","author":"Shen T.","year":"2023","unstructured":"T. Shen, R. Jin, Y. Huang, C. Liu, W. Dong, Z. Guo, X. Wu, Y. Liu, and D. Xiong. Large language model alignment: A survey. arXiv preprint arXiv:2309.15025, 2023."},{"key":"e_1_2_1_114_1","volume-title":"Unchosen experts can contribute too: Unleashing moe models","author":"Shi C.","year":"2024","unstructured":"C. Shi, C. Yang, X. Zhu, J.Wang, T.Wu, S. Li, D. Cai, Y. Yang, and Y. Meng. Unchosen experts can contribute too: Unleashing moe models\u2019 power by selfcontrast. arXiv preprint arXiv:2405.14507, 2024."},{"key":"e_1_2_1_115_1","volume-title":"A thorough examination of decoding methods in the era of llms. arXiv preprint arXiv:2402.06925","author":"Shi C.","year":"2024","unstructured":"C. Shi, H. Yang, D. Cai, Z. Zhang, Y. Wang, Y. Yang, and W. Lam. A thorough examination of decoding methods in the era of llms. arXiv preprint arXiv:2402.06925, 2024."},{"key":"e_1_2_1_116_1","volume-title":"Trusting your evidence: Hallucinate less with context-aware decoding. arXiv preprint arXiv:2305.14739","author":"Shi W.","year":"2023","unstructured":"W. Shi, X. Han, M. Lewis, Y. Tsvetkov, L. Zettlemoyer, and S. W.-t. Yih. Trusting your evidence: Hallucinate less with context-aware decoding. arXiv preprint arXiv:2305.14739, 2023."},{"key":"e_1_2_1_117_1","volume-title":"Autoprompt: Eliciting knowledge from language models with automatically generated prompts. arXiv preprint arXiv:2010.15980","author":"Shin T.","year":"2020","unstructured":"T. Shin, Y. Razeghi, R. L. Logan IV, E. Wallace, and S. Singh. Autoprompt: Eliciting knowledge from language models with automatically generated prompts. arXiv preprint arXiv:2010.15980, 2020."},{"key":"e_1_2_1_118_1","volume-title":"Using deepspeed and megatron to train megatron-turing nlg 530b, a large-scale generative language model. arXiv preprint arXiv:2201.11990","author":"Smith S.","year":"2022","unstructured":"S. Smith, M. Patwary, B. Norick, P. LeGresley, S. Rajbhandari, J. Casper, Z. Liu, S. Prabhumoye, G. Zerveas, V. Korthikanti, et al. Using deepspeed and megatron to train megatron-turing nlg 530b, a large-scale generative language model. arXiv preprint arXiv:2201.11990, 2022."},{"key":"e_1_2_1_119_1","first-page":"31","article-title":"Blockwise parallel decoding for deep autoregressive models","author":"Stern M.","year":"2018","unstructured":"M. Stern, N. Shazeer, and J. Uszkoreit. Blockwise parallel decoding for deep autoregressive models. Advances in Neural Information Processing Systems, 31, 2018.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_120_1","first-page":"3008","article-title":"Learning to summarize with human feedback","volume":"33","author":"Stiennon N.","year":"2020","unstructured":"N. Stiennon, L. Ouyang, J. Wu, D. Ziegler, R. Lowe, C. Voss, A. Radford, D. Amodei, and P. F. Christiano. Learning to summarize with human feedback. Advances in Neural Information Processing Systems, 33:3008-3021, 2020.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_121_1","volume-title":"Seesaw: High-throughput llm inference via model resharding. arXiv preprint arXiv:2503.06433","author":"Su Q.","year":"2025","unstructured":"Q. Su, W. Zhao, X. Li, M. Andoorveedu, C. Jiang, Z. Zhu, K. Song, C. Giannoula, and G. Pekhimenko. Seesaw: High-throughput llm inference via model resharding. arXiv preprint arXiv:2503.06433, 2025."},{"key":"e_1_2_1_122_1","volume-title":"Contrastive search is what you need for neural text generation. arXiv preprint arXiv:2210.14140","author":"Su Y.","year":"2022","unstructured":"Y. Su and N. Collier. Contrastive search is what you need for neural text generation. arXiv preprint arXiv:2210.14140, 2022."},{"key":"e_1_2_1_123_1","first-page":"21548","article-title":"A contrastive framework for neural text generation","volume":"35","author":"Su Y.","year":"2022","unstructured":"Y. Su, T. Lan, Y. Wang, D. Yogatama, L. Kong, and N. Collier. A contrastive framework for neural text generation. Advances in Neural Information Processing Systems, 35:21548-21561, 2022.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_124_1","volume-title":"Extracting latent steering vectors from pretrained language models. arXiv preprint arXiv:2205.05124","author":"Subramani N.","year":"2022","unstructured":"N. Subramani, N. Suresh, and M. E. Peters. Extracting latent steering vectors from pretrained language models. arXiv preprint arXiv:2205.05124, 2022."},{"key":"e_1_2_1_125_1","volume-title":"et al. Trustllm: Trustworthiness in large language models. arXiv preprint arXiv:2401.05561","author":"Sun L.","year":"2024","unstructured":"L. Sun, Y. Huang, H. Wang, S. Wu, Q. Zhang, C. Gao, Y. Huang, W. Lyu, Y. Zhang, X. Li, et al. Trustllm: Trustworthiness in large language models. arXiv preprint arXiv:2401.05561, 2024."},{"key":"e_1_2_1_126_1","first-page":"36","article-title":"Glober: coherent non-autoregressive video generation via global guided video decoder","author":"Sun M.","year":"2024","unstructured":"M. Sun, W.Wang, Z. Qin, J. Sun, S. Chen, and J. Liu. Glober: coherent non-autoregressive video generation via global guided video decoder. Advances in Neural Information Processing Systems, 36, 2024.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_127_1","volume-title":"Instantaneous grammatical error correction with shallow aggressive decoding. arXiv preprint arXiv:2106.04970","author":"Sun X.","year":"2021","unstructured":"X. Sun, T. Ge, F. Wei, and H. Wang. Instantaneous grammatical error correction with shallow aggressive decoding. arXiv preprint arXiv:2106.04970, 2021."},{"key":"e_1_2_1_128_1","volume-title":"Outdated issue aware decoding for factual knowledge editing. arXiv preprint arXiv:2406.02882","author":"Sun Z.","year":"2024","unstructured":"Z. Sun, Y. Liu, J.Wang, F. Meng, J. Xu, Y. Chen, and J. Zhou. Outdated issue aware decoding for factual knowledge editing. arXiv preprint arXiv:2406.02882, 2024."},{"key":"e_1_2_1_129_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475591"},{"key":"e_1_2_1_130_1","volume-title":"Hart: Efficient visual generation with hybrid autoregressive transformer. arXiv preprint arXiv:2410.10812","author":"Tang H.","year":"2024","unstructured":"H. Tang, Y. Wu, S. Yang, E. Xie, J. Chen, J. Chen, Z. Zhang, H. Cai, Y. Lu, and S. Han. Hart: Efficient visual generation with hybrid autoregressive transformer. arXiv preprint arXiv:2410.10812, 2024."},{"key":"e_1_2_1_131_1","volume-title":"Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805","author":"Team G.","year":"2023","unstructured":"G. Team, R. Anil, S. Borgeaud, Y. Wu, J.-B. Alayrac, J. Yu, R. Soricut, J. Schalkwyk, A. M. Dai, A. Hauth, et al. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805, 2023."},{"key":"e_1_2_1_132_1","volume-title":"Accelerating auto-regressive text-toimage generation with training-free speculative jacobi decoding. arXiv preprint arXiv:2410.01699","author":"Teng Y.","year":"2024","unstructured":"Y. Teng, H. Shi, X. Liu, X. Ning, G. Dai, Y. Wang, Z. Li, and X. Liu. Accelerating auto-regressive text-toimage generation with training-free speculative jacobi decoding. arXiv preprint arXiv:2410.01699, 2024."},{"key":"e_1_2_1_133_1","volume-title":"arXiv preprint arXiv:1905.05950","author":"Tenney I.","year":"2019","unstructured":"I. Tenney. Bert rediscovers the classical nlp pipeline. arXiv preprint arXiv:1905.05950, 2019."},{"key":"e_1_2_1_134_1","volume-title":"Selective prompt anchoring for code generation. arXiv preprint arXiv:2408.09121","author":"Tian Y.","year":"2024","unstructured":"Y. Tian and T. Zhang. Selective prompt anchoring for code generation. arXiv preprint arXiv:2408.09121, 2024."},{"key":"e_1_2_1_135_1","volume-title":"Attention reallocation: Towards zero-cost and controllable hallucination mitigation of mllms. arXiv preprint arXiv:2503.08342","author":"Tu C.","year":"2025","unstructured":"C. Tu, P. Ye, D. Zhou, L. Bai, G. Yu, T. Chen, and W. Ouyang. Attention reallocation: Towards zero-cost and controllable hallucination mitigation of mllms. arXiv preprint arXiv:2503.08342, 2025."},{"key":"e_1_2_1_136_1","volume-title":"Activation addition: Steering language models without optimization. arXiv e-prints","author":"Turner A. M.","year":"2023","unstructured":"A. M. Turner, L. Thiergart, G. Leech, D. Udell, J. J. Vazquez, U. Mini, and M. MacDiarmid. Activation addition: Steering language models without optimization. arXiv e-prints, pages arXiv-2308, 2023."},{"key":"e_1_2_1_137_1","volume-title":"Efficient reinforcement learning for unsupervised controlled text generation. arXiv preprint arXiv:2204.07696","author":"Upadhyay B.","year":"2022","unstructured":"B. Upadhyay, A. Sudhakar, and A. Maheswaran. Efficient reinforcement learning for unsupervised controlled text generation. arXiv preprint arXiv:2204.07696, 2022."},{"key":"e_1_2_1_138_1","volume-title":"Diverse beam search: Decoding diverse solutions from neural sequence models. arXiv preprint arXiv:1610.02424","author":"Vijayakumar A. K.","year":"2016","unstructured":"A. K. Vijayakumar, M. Cogswell, R. R. Selvaraju, Q. Sun, S. Lee, D. Crandall, and D. Batra. Diverse beam search: Decoding diverse solutions from neural sequence models. arXiv preprint arXiv:1610.02424, 2016."},{"key":"e_1_2_1_139_1","volume-title":"Mllm can see? dynamic correction decoding for hallucination mitigation. arXiv preprint arXiv:2410.11779","author":"Wang C.","year":"2024","unstructured":"C.Wang, X. Chen, N. Zhang, B. Tian, H. Xu, S. Deng, and H. Chen. Mllm can see? dynamic correction decoding for hallucination mitigation. arXiv preprint arXiv:2410.11779, 2024."},{"key":"e_1_2_1_140_1","volume-title":"Explainable claim verification via knowledge-grounded reasoning with large language models. arXiv preprint arXiv:2310.05253","author":"Wang H.","year":"2023","unstructured":"H. Wang and K. Shu. Explainable claim verification via knowledge-grounded reasoning with large language models. arXiv preprint arXiv:2310.05253, 2023."},{"key":"e_1_2_1_141_1","doi-asserted-by":"crossref","first-page":"2347","DOI":"10.1145\/3627673.3679821","volume-title":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","author":"Wang H.","year":"2024","unstructured":"H. Wang and K. Shu. Trojan activation attack: Redteaming large language models using steering vectors for safety-alignment. In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, pages 2347-2357, 2024."},{"key":"e_1_2_1_142_1","volume-title":"Probing the safety response boundary of large language models via unsafe decoding path generation. arXiv preprint arXiv:2408.10668","author":"Wang H.","year":"2024","unstructured":"H. Wang, B. Wu, Y. Bian, Y. Chang, X. Wang, and P. Zhao. Probing the safety response boundary of large language models via unsafe decoding path generation. arXiv preprint arXiv:2408.10668, 2024."},{"key":"e_1_2_1_143_1","volume-title":"Privacyaware decoding: Mitigating privacy leakage of large language models in retrieval-augmented generation. arXiv preprint arXiv:2508.03098","author":"Wang H.","year":"2025","unstructured":"H. Wang, X. Xu, B. Huang, and K. Shu. Privacyaware decoding: Mitigating privacy leakage of large language models in retrieval-augmented generation. arXiv preprint arXiv:2508.03098, 2025."},{"key":"e_1_2_1_144_1","volume-title":"Valid: Mitigating the hallucination of large vision language models by visual layer fusion contrastive decoding. arXiv preprint arXiv:2411.15839","author":"Wang J.","year":"2024","unstructured":"J. Wang, Y. Gao, and J. Sang. Valid: Mitigating the hallucination of large vision language models by visual layer fusion contrastive decoding. arXiv preprint arXiv:2411.15839, 2024."},{"key":"e_1_2_1_145_1","volume-title":"Inferaligner: Inference-time alignment for harmlessness through cross-model guidance. arXiv preprint arXiv:2401.11206","author":"Wang P.","year":"2024","unstructured":"P. Wang, D. Zhang, L. Li, C. Tan, X. Wang, K. Ren, B. Jiang, and X. Qiu. Inferaligner: Inference-time alignment for harmlessness through cross-model guidance. arXiv preprint arXiv:2401.11206, 2024."},{"key":"e_1_2_1_146_1","volume-title":"Uscd: Improving code generation of llms by uncertainty-aware selective contrastive decoding. arXiv preprint arXiv:2409.05923","author":"Wang S.","year":"2024","unstructured":"S. Wang, L. Ding, L. Shen, Y. Luo, Z. He, W. Yu, and D. Tao. Uscd: Improving code generation of llms by uncertainty-aware selective contrastive decoding. arXiv preprint arXiv:2409.05923, 2024."},{"key":"e_1_2_1_147_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"e_1_2_1_148_1","volume-title":"Mitigating hallucinations in large vision-language models with instruction contrastive decoding. arXiv preprint arXiv:2403.18715","author":"Wang X.","year":"2024","unstructured":"X. Wang, J. Pan, L. Ding, and C. Biemann. Mitigating hallucinations in large vision-language models with instruction contrastive decoding. arXiv preprint arXiv:2403.18715, 2024."},{"key":"e_1_2_1_149_1","volume-title":"Chain-of-thought reasoning without prompting. arXiv preprint arXiv:2402.10200","author":"Wang X.","year":"2024","unstructured":"X. Wang and D. Zhou. Chain-of-thought reasoning without prompting. arXiv preprint arXiv:2402.10200, 2024."},{"key":"e_1_2_1_150_1","volume-title":"Speculative rag: Enhancing retrieval augmented generation through drafting. arXiv preprint arXiv:2407.08223","author":"Wang Z.","year":"2024","unstructured":"Z. Wang, Z. Wang, L. Le, H. S. Zheng, S. Mishra, V. Perot, Y. Zhang, A. Mattapalli, A. Taly, J. Shang, et al. Speculative rag: Enhancing retrieval augmented generation through drafting. arXiv preprint arXiv:2407.08223, 2024."},{"key":"e_1_2_1_151_1","volume-title":"Seed: Accelerating reasoning tree construction via scheduled speculative decoding. arXiv preprint arXiv:2406.18200","author":"Wang Z.","year":"2024","unstructured":"Z. Wang, J. Wu, Y. Lai, C. Zhang, and D. Zhou. Seed: Accelerating reasoning tree construction via scheduled speculative decoding. arXiv preprint arXiv:2406.18200, 2024."},{"key":"e_1_2_1_152_1","volume-title":"Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652","author":"Wei J.","year":"2021","unstructured":"J. Wei, M. Bosma, V. Y. Zhao, K. Guu, A. W. Yu, B. Lester, N. Du, A. M. Dai, and Q. V. Le. Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652, 2021."},{"key":"e_1_2_1_153_1","first-page":"4913","article-title":"Naturalprover: Grounded mathematical proof generation with language models","volume":"35","author":"Welleck S.","year":"2022","unstructured":"S. Welleck, J. Liu, X. Lu, H. Hajishirzi, and Y. Choi. Naturalprover: Grounded mathematical proof generation with language models. Advances in Neural Information Processing Systems, 35:4913-4927, 2022.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_154_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00502"},{"key":"e_1_2_1_155_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.257"},{"key":"e_1_2_1_156_1","volume-title":"Swift: On-the-fly self-speculative decoding for llm inference acceleration. arXiv preprint arXiv:2410.06916","author":"Xia H.","year":"2024","unstructured":"H. Xia, Y. Li, J. Zhang, C. Du, and W. Li. Swift: On-the-fly self-speculative decoding for llm inference acceleration. arXiv preprint arXiv:2410.06916, 2024."},{"key":"e_1_2_1_157_1","volume-title":"Unlocking efficiency in large language model inference: A comprehensive survey of speculative decoding. arXiv preprint arXiv:2401.07851","author":"Xia H.","year":"2024","unstructured":"H. Xia, Z. Yang, Q. Dong, P. Wang, Y. Li, T. Ge, T. Liu, W. Li, and Z. Sui. Unlocking efficiency in large language model inference: A comprehensive survey of speculative decoding. arXiv preprint arXiv:2401.07851, 2024."},{"key":"e_1_2_1_158_1","doi-asserted-by":"crossref","first-page":"7655","DOI":"10.18653\/v1\/2024.findings-acl.456","volume-title":"Findings of the Association for Computational Linguistics: ACL 2024","author":"Xia H.","year":"2024","unstructured":"H. Xia, Z. Yang, Q. Dong, P. Wang, Y. Li, T. Ge, T. Liu, W. Li, and Z. Sui. Unlocking efficiency in large language model inference: A comprehensive survey of speculative decoding. In L.-W. Ku, A. Martins, and V. Srikumar, editors, Findings of the Association for Computational Linguistics: ACL 2024, pages 7655- 7671, Bangkok, Thailand, Aug. 2024. Association for Computational Linguistics."},{"key":"e_1_2_1_159_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Xie Y.","year":"2023","unstructured":"Y. Xie, K. Kawaguchi, Y. Zhao, X. Zhao, M.-Y. Kan, J. He, and Q. Xie. Self-evaluation guided beam search for reasoning. In Thirty-seventh Conference on Neural Information Processing Systems, 2023."},{"key":"e_1_2_1_160_1","volume-title":"Mitigating hallucinations of large language models in medical information extraction via contrastive decoding. arXiv preprint arXiv:2410.15702","author":"Xu D.","year":"2024","unstructured":"D. Xu, Z. Zhang, Z. Zhu, Z. Lin, Q. Liu, X. Wu, T. Xu, X. Zhao, Y. Zheng, and E. Chen. Mitigating hallucinations of large language models in medical information extraction via contrastive decoding. arXiv preprint arXiv:2410.15702, 2024."},{"key":"e_1_2_1_161_1","volume-title":"Safedecoding: Defending against jailbreak attacks via safety-aware decoding. arXiv preprint arXiv:2402.08983","author":"Xu Z.","year":"2024","unstructured":"Z. Xu, F. Jiang, L. Niu, J. Jia, B. Y. Lin, and R. Poovendran. Safedecoding: Defending against jailbreak attacks via safety-aware decoding. arXiv preprint arXiv:2402.08983, 2024."},{"key":"e_1_2_1_162_1","volume-title":"Improving factuality in large language models via decoding-time hallucinatory and truthful comparators. arXiv preprint arXiv:2408.12325","author":"Yang D.","year":"2024","unstructured":"D. Yang, D. Xiao, J. Wei, M. Li, Z. Chen, K. Li, and L. Zhang. Improving factuality in large language models via decoding-time hallucinatory and truthful comparators. arXiv preprint arXiv:2408.12325, 2024."},{"key":"e_1_2_1_163_1","volume-title":"A frustratingly simple decoding method for neural text generation. arXiv preprint arXiv:2305.12675","author":"Yang H.","year":"2023","unstructured":"H. Yang, D. Cai, H. Li, W. Bi, W. Lam, and S. Shi. A frustratingly simple decoding method for neural text generation. arXiv preprint arXiv:2305.12675, 2023."},{"key":"e_1_2_1_164_1","volume-title":"Fudge: Controlled text generation with future discriminators. arXiv preprint arXiv:2104.05218","author":"Yang K.","year":"2021","unstructured":"K. Yang and D. Klein. Fudge: Controlled text generation with future discriminators. arXiv preprint arXiv:2104.05218, 2021."},{"key":"e_1_2_1_165_1","volume-title":"Breaking the beam search curse: A study of (re-) scoring methods and stopping criteria for neural machine translation. arXiv preprint arXiv:1808.09582","author":"Yang Y.","year":"2018","unstructured":"Y. Yang, L. Huang, and M. Ma. Breaking the beam search curse: A study of (re-) scoring methods and stopping criteria for neural machine translation. arXiv preprint arXiv:1808.09582, 2018."},{"key":"e_1_2_1_166_1","volume-title":"Speculative contrastive decoding. arXiv preprint arXiv:2311.08981","author":"Yuan H.","year":"2023","unstructured":"H. Yuan, K. Lu, F. Huang, Z. Yuan, and C. Zhou. Speculative contrastive decoding. arXiv preprint arXiv:2311.08981, 2023."},{"key":"e_1_2_1_167_1","volume-title":"Technical report: Auxiliary tuning and its application to conditional text generation. arXiv preprint arXiv:2006.16823","author":"Zeldes Y.","year":"2020","unstructured":"Y. Zeldes, D. Padnos, O. Sharir, and B. Peleg. Technical report: Auxiliary tuning and its application to conditional text generation. arXiv preprint arXiv:2006.16823, 2020."},{"key":"e_1_2_1_168_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657746"},{"key":"e_1_2_1_169_1","volume-title":"Root defence strategies: Ensuring safety of llm at the decoding level. arXiv preprint arXiv:2410.06809","author":"Zeng X.","year":"2024","unstructured":"X. Zeng, Y. Shang, Y. Zhu, J. Chen, and Y. Tian. Root defence strategies: Ensuring safety of llm at the decoding level. arXiv preprint arXiv:2410.06809, 2024."},{"key":"e_1_2_1_170_1","volume-title":"Token-level direct preference optimization. arXiv preprint arXiv:2404.11999","author":"Zeng Y.","year":"2024","unstructured":"Y. Zeng, G. Liu, W. Ma, N. Yang, H. Zhang, and J. Wang. Token-level direct preference optimization. arXiv preprint arXiv:2404.11999, 2024."},{"key":"e_1_2_1_171_1","volume-title":"Controllable text generation with residual memory transformer. arXiv preprint arXiv:2309.16231","author":"Zhang H.","year":"2023","unstructured":"H. Zhang, S. Si, H.Wu, and D. Song. Controllable text generation with residual memory transformer. arXiv preprint arXiv:2309.16231, 2023."},{"key":"e_1_2_1_172_1","volume-title":"Discup: Discriminator cooperative unlikelihood prompt-tuning for controllable text generation. arXiv preprint arXiv:2210.09551","author":"Zhang H.","year":"2022","unstructured":"H. Zhang and D. Song. Discup: Discriminator cooperative unlikelihood prompt-tuning for controllable text generation. arXiv preprint arXiv:2210.09551, 2022."},{"key":"e_1_2_1_173_1","volume-title":"Draft & verify: Lossless large language model acceleration via self-speculative decoding. arXiv preprint arXiv:2309.08168","author":"Zhang J.","year":"2023","unstructured":"J. Zhang, J. Wang, H. Li, L. Shou, K. Chen, G. Chen, and S. Mehrotra. Draft & verify: Lossless large language model acceleration via self-speculative decoding. arXiv preprint arXiv:2309.08168, 2023."},{"key":"e_1_2_1_174_1","volume-title":"Planning with large language models for code generation. arXiv preprint arXiv:2303.05510","author":"Zhang S.","year":"2023","unstructured":"S. Zhang, Z. Chen, Y. Shen, M. Ding, J. B. Tenenbaum, and C. Gan. Planning with large language models for code generation. arXiv preprint arXiv:2303.05510, 2023."},{"key":"e_1_2_1_175_1","volume-title":"The knowledge alignment problem: Bridging human and external knowledge for large language models. arXiv preprint arXiv:2305.13669","author":"Zhang S.","year":"2023","unstructured":"S. Zhang, L. Pan, J. Zhao, and W. Y. Wang. The knowledge alignment problem: Bridging human and external knowledge for large language models. arXiv preprint arXiv:2305.13669, 2023."},{"key":"e_1_2_1_176_1","volume-title":"Truthx: Alleviating hallucinations by editing large language models in truthful space. arXiv preprint arXiv:2402.17811","author":"Zhang S.","year":"2024","unstructured":"S. Zhang, T. Yu, and Y. Feng. Truthx: Alleviating hallucinations by editing large language models in truthful space. arXiv preprint arXiv:2402.17811, 2024."},{"key":"e_1_2_1_177_1","doi-asserted-by":"crossref","first-page":"190","DOI":"10.18653\/v1\/2023.acl-long.11","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Zhang X.","year":"2023","unstructured":"X. Zhang and X. Wan. Mil-decoding: Detoxifying language models at token-level via multiple instance learning. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 190-202, 2023."},{"key":"e_1_2_1_178_1","volume-title":"Enhancing contextual understanding in large language models through contrastive decoding. arXiv preprint arXiv:2405.02750","author":"Zhao Z.","year":"2024","unstructured":"Z. Zhao, E. Monti, J. Lehmann, and H. Assem. Enhancing contextual understanding in large language models through contrastive decoding. arXiv preprint arXiv:2405.02750, 2024."},{"key":"e_1_2_1_179_1","volume-title":"Adversarial contrastive decoding: Boosting safety alignment of large language models via opposite prompt optimization. arXiv preprint arXiv:2406.16743","author":"Zhao Z.","year":"2024","unstructured":"Z. Zhao, X. Zhang, K. Xu, X. Hu, R. Zhang, Z. Du, Q. Guo, and Y. Chen. Adversarial contrastive decoding: Boosting safety alignment of large language models via opposite prompt optimization. arXiv preprint arXiv:2406.16743, 2024."},{"key":"e_1_2_1_180_1","volume-title":"Llm4brain: Training a large language model for brain video understanding. arXiv preprint arXiv:2409.17987","author":"Zheng R.","year":"2024","unstructured":"R. Zheng and L. Sun. Llm4brain: Training a large language model for brain video understanding. arXiv preprint arXiv:2409.17987, 2024."},{"key":"e_1_2_1_181_1","volume-title":"Toward unified controllable text generation via regular expression instruction. arXiv preprint arXiv:2309.10447","author":"Zheng X.","year":"2023","unstructured":"X. Zheng, H. Lin, X. Han, and L. Sun. Toward unified controllable text generation via regular expression instruction. arXiv preprint arXiv:2309.10447, 2023."},{"key":"e_1_2_1_182_1","volume-title":"Rose doesn\u2019t do that: Boosting the safety of instructiontuned large language models with reverse prompt contrastive decoding. arXiv preprint arXiv:2402.11889","author":"Zhong Q.","year":"2024","unstructured":"Q. Zhong, L. Ding, J. Liu, B. Du, and D. Tao. Rose doesn\u2019t do that: Boosting the safety of instructiontuned large language models with reverse prompt contrastive decoding. arXiv preprint arXiv:2402.11889, 2024."},{"key":"e_1_2_1_183_1","first-page":"42602","volume-title":"International Conference on Machine Learning","author":"Zhou W.","year":"2023","unstructured":"W. Zhou, Y. E. Jiang, E. Wilcox, R. Cotterell, and M. Sachan. Controlled text generation with natural language instructions. In International Conference on Machine Learning, pages 42602-42613. PMLR, 2023."},{"key":"e_1_2_1_184_1","volume-title":"Distillspec: Improving speculative decoding via knowledge distillation. arXiv preprint arXiv:2310.08461","author":"Zhou Y.","year":"2023","unstructured":"Y. Zhou, K. Lyu, A. S. Rawat, A. K. Menon, A. Rostamizadeh, S. Kumar, J.-F. Kagy, and R. Agarwal. Distillspec: Improving speculative decoding via knowledge distillation. arXiv preprint arXiv:2310.08461, 2023."},{"key":"e_1_2_1_185_1","volume-title":"Ibd: Alleviating hallucinations in large vision-language models via image-biased decoding. arXiv preprint arXiv:2402.18476","author":"Zhu L.","year":"2024","unstructured":"L. Zhu, D. Ji, T. Chen, P. Xu, J. Ye, and J. Liu. Ibd: Alleviating hallucinations in large vision-language models via image-biased decoding. arXiv preprint arXiv:2402.18476, 2024."},{"key":"e_1_2_1_186_1","volume-title":"Deductive beam search: Decoding deducible rationale for chain-ofthought reasoning. arXiv preprint arXiv:2401.17686","author":"Zhu T.","year":"2024","unstructured":"T. Zhu, K. Zhang, J. Xie, and Y. Su. Deductive beam search: Decoding deducible rationale for chain-ofthought reasoning. arXiv preprint arXiv:2401.17686, 2024."},{"key":"e_1_2_1_187_1","volume-title":"Improving code generation by dynamic temperature sampling. arXiv preprint arXiv:2309.02772","author":"Zhu Y.","year":"2023","unstructured":"Y. Zhu, J. A. Li, G. Li, Y. Zhao, J. Li, Z. Jin, and H. Mei. Improving code generation by dynamic temperature sampling. arXiv preprint arXiv:2309.02772, 2023."},{"key":"e_1_2_1_188_1","volume-title":"Hierarchical skip decoding for efficient autoregressive text generation. arXiv preprint arXiv:2403.14919","author":"Zhu Y.","year":"2024","unstructured":"Y. Zhu, X. Yang, Y. Wu, and W. Zhang. Hierarchical skip decoding for efficient autoregressive text generation. arXiv preprint arXiv:2403.14919, 2024."}],"container-title":["ACM SIGKDD Explorations Newsletter"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3820356.3820357","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T15:59:25Z","timestamp":1781711965000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3820356.3820357"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,17]]},"references-count":188,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,6,17]]}},"alternative-id":["10.1145\/3820356.3820357"],"URL":"https:\/\/doi.org\/10.1145\/3820356.3820357","relation":{},"ISSN":["1931-0145","1931-0153"],"issn-type":[{"value":"1931-0145","type":"print"},{"value":"1931-0153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,17]]},"assertion":[{"value":"2026-06-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}