{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T01:40:16Z","timestamp":1783474816571,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":130,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-21-10198"],"award-info":[{"award-number":["W911NF-21-10198"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Department of Homeland Security","award":["17STCIN00001-05-00"],"award-info":[{"award-number":["17STCIN00001-05-00"]}]},{"name":"Cisco Faculty Research Award"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3736563","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T20:52:41Z","timestamp":1754254361000},"page":"6173-6183","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["A Survey on Small Language Models in the Era of Large Language Models: Architecture, Capabilities, and Trustworthiness"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8321-6365","authenticated-orcid":false,"given":"Fali","family":"Wang","sequence":"first","affiliation":[{"name":"The Pennsylvania State University, University Park, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1591-7172","authenticated-orcid":false,"given":"Minhua","family":"Lin","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University, University Park, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4985-8724","authenticated-orcid":false,"given":"Yao","family":"Ma","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9032-6413","authenticated-orcid":false,"given":"Hui","family":"Liu","sequence":"additional","affiliation":[{"name":"Amazon, Palo Alto, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5257-6843","authenticated-orcid":false,"given":"Qi","family":"He","sequence":"additional","affiliation":[{"name":"Amazon, Palo Alto, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1554-2761","authenticated-orcid":false,"given":"Xianfeng","family":"Tang","sequence":"additional","affiliation":[{"name":"Amazon, Palo Alto, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7125-3898","authenticated-orcid":false,"given":"Jiliang","family":"Tang","sequence":"additional","affiliation":[{"name":"Michigan State University, East Lansing, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2200-8711","authenticated-orcid":false,"given":"Jian","family":"Pei","sequence":"additional","affiliation":[{"name":"Duke University, Durham, NC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3448-4878","authenticated-orcid":false,"given":"Suhang","family":"Wang","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University, University Park, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Ammar Ahmad Awan, Jyoti Aneja, Ahmed Awadallah, Hany Awadalla, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Harkirat Behl, et al.","author":"Abdin Marah","year":"2024","unstructured":"Marah Abdin, Sam Ade Jacobs, Ammar Ahmad Awan, Jyoti Aneja, Ahmed Awadallah, Hany Awadalla, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Harkirat Behl, et al. 2024. Phi-3 technical report: A highly capable language model locally on your phone. arXiv preprint arXiv:2404.14219 (2024)."},{"key":"e_1_3_2_1_2_1","volume-title":"Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs. arXiv preprint arXiv:2503.01743","author":"Abouelenin Abdelrahman","year":"2025","unstructured":"Abdelrahman Abouelenin, Atabak Ashfaq, Adam Atkinson, Hany Awadalla, Nguyen Bach, Jianmin Bao, Alon Benhaim, Martin Cai, Vishrav Chaudhary, Congcong Chen, et al. 2025. Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs. arXiv preprint arXiv:2503.01743 (2025)."},{"key":"e_1_3_2_1_3_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"Deep Learning using Rectified Linear Units (ReLU). CoRR","author":"Agarap Abien Fred","year":"2018","unstructured":"Abien Fred Agarap. 2018. Deep Learning using Rectified Linear Units (ReLU). CoRR, Vol. abs\/1803.08375 (2018). showeprint[arXiv]1803.08375 http:\/\/arxiv.org\/abs\/1803.08375"},{"key":"e_1_3_2_1_5_1","unstructured":"Meta AI. 2024. Llama 3.2: Revolutionizing edge AI and vision with open customizable models. https:\/\/ai.meta.com\/blog\/llama-3-2-connect-2024-vision-edge-mobile-devices\/ Accessed: 2024-9-25."},{"key":"e_1_3_2_1_6_1","volume-title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints. arxiv: 2305.13245 [cs.CL] https:\/\/arxiv.org\/abs\/2305.13245","author":"Ainslie Joshua","year":"2023","unstructured":"Joshua Ainslie, James Lee-Thorp, Michiel de Jong, Yury Zemlyanskiy, Federico Lebr\u00f3n, and Sumit Sanghai. 2023. GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints. arxiv: 2305.13245 [cs.CL] https:\/\/arxiv.org\/abs\/2305.13245"},{"key":"e_1_3_2_1_7_1","unstructured":"Ali Al-Lawati Jason Lucas Zhiwei Zhang Prasenjit Mitra and Suhang Wang. 2025. Graph-based Molecular In-context Learning Grounded on Morgan Fingerprints. arxiv: 2502.05414 [cs.LG] https:\/\/arxiv.org\/abs\/2502.05414"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.3390\/ai5030071"},{"key":"e_1_3_2_1_9_1","volume-title":"Guilherme Penedo, Lewis Tunstall, Andr\u00e9s Marafioti, Hynek Kydl\u00edek, Agust\u00edn Piqueres Lajar\u00edn, Vaibhav Srivastav, et al.","author":"Allal Loubna Ben","year":"2025","unstructured":"Loubna Ben Allal, Anton Lozhkov, Elie Bakouch, Gabriel Mart\u00edn Bl\u00e1zquez, Guilherme Penedo, Lewis Tunstall, Andr\u00e9s Marafioti, Hynek Kydl\u00edek, Agust\u00edn Piqueres Lajar\u00edn, Vaibhav Srivastav, et al. 2025. SmolLM2: When Smol Goes Big-Data-Centric Training of a Small Language Model. arXiv preprint arXiv:2502.02737 (2025)."},{"key":"e_1_3_2_1_10_1","unstructured":"Loubna Ben Allal Anton Lozhkov Elie Bakouch Leandro von Werra and Thomas Wolf. 2024. SmolLM - blazingly fast and remarkably powerful."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.68"},{"key":"e_1_3_2_1_12_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang Binyuan Hui Luo Ji Mei Li Junyang Lin Runji Lin Dayiheng Liu Gao Liu Chengqiang Lu Keming Lu Jianxin Ma Rui Men Xingzhang Ren Xuancheng Ren Chuanqi Tan Sinan Tan Jianhong Tu Peng Wang Shijie Wang Wei Wang Shengguang Wu Benfeng Xu Jin Xu An Yang Hao Yang Jian Yang Shusheng Yang Yang Yao Bowen Yu Hongyi Yuan Zheng Yuan Jianwei Zhang Xingxuan Zhang Yichang Zhang Zhenru Zhang Chang Zhou Jingren Zhou Xiaohuan Zhou and Tianhang Zhu. 2023. Qwen Technical Report. arxiv: 2309.16609 [cs.CL] https:\/\/arxiv.org\/abs\/2309.16609"},{"key":"e_1_3_2_1_13_1","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=ARAxPPIAhq","author":"Beck Maximilian","year":"2024","unstructured":"Maximilian Beck, Korbinian P\u00f6ppel, Markus Spanring, Andreas Auer, Oleksandra Prudnikova, Michael K Kopp, G\u00fcnter Klambauer, Johannes Brandstetter, and Sepp Hochreiter. 2024. xLS\u2122: Extended Long Short-Term Memory. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=ARAxPPIAhq"},{"key":"e_1_3_2_1_14_1","unstructured":"Marco Bellagente Jonathan Tow Dakota Mahan Duy Phung Maksym Zhuravinskyi Reshinth Adithyan James Baicoianu Ben Brooks Nathan Cooper Ashish Datta et al. 2024. Stable lm 2 1.6 b technical report. arXiv preprint arXiv:2402.17834 (2024)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.485"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning. 4971-5012","author":"Burns Collin","year":"2024","unstructured":"Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner, Bowen Baker, Leo Gao, Leopold Aschenbrenner, Yining Chen, Adrien Ecoffet, Manas Joglekar, Jan Leike, et al. 2024. Weak-to-strong generalization: eliciting strong capabilities with weak supervision. In Proceedings of the 41st International Conference on Machine Learning. 4971-5012."},{"key":"e_1_3_2_1_17_1","first-page":"2633","volume-title":"30th USENIX Security Symposium (USENIX Security 21)","author":"Carlini Nicholas","year":"2021","unstructured":"Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Ulfar Erlingsson, et al. 2021. Extracting training data from large language models. In 30th USENIX Security Symposium (USENIX Security 21). 2633-2650."},{"key":"e_1_3_2_1_18_1","volume-title":"OR-Bench: An Over-Refusal Benchmark for Large Language Models. arXiv preprint arXiv:2405.20947","author":"Cui Justin","year":"2024","unstructured":"Justin Cui, Wei-Lin Chiang, Ion Stoica, and Cho-Jui Hsieh. 2024. OR-Bench: An Over-Refusal Benchmark for Large Language Models. arXiv preprint arXiv:2405.20947 (2024)."},{"key":"e_1_3_2_1_19_1","volume-title":"Fft: Towards harmlessness evaluation and analysis for llms with factuality, fairness, toxicity. arXiv preprint arXiv:2311.18580","author":"Cui Shiyao","year":"2023","unstructured":"Shiyao Cui, Zhenyu Zhang, Yilong Chen, Wenyuan Zhang, Tianyun Liu, Siqi Wang, and Tingwen Liu. 2023. Fft: Towards harmlessness evaluation and analysis for llms with factuality, fairness, toxicity. arXiv preprint arXiv:2311.18580 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality. arXiv preprint arXiv:2405.21060","author":"Dao Tri","year":"2024","unstructured":"Tri Dao and Albert Gu. 2024. Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality. arXiv preprint arXiv:2405.21060 (2024)."},{"key":"e_1_3_2_1_21_1","volume-title":"Questioning the survey responses of large language models. arXiv preprint arXiv:2306.07951","author":"Dominguez-Olmedo Ricardo","year":"2023","unstructured":"Ricardo Dominguez-Olmedo, Moritz Hardt, and Celestine Mendler-D\u00fcnner. 2023. Questioning the survey responses of large language models. arXiv preprint arXiv:2306.07951 (2023)."},{"key":"e_1_3_2_1_22_1","volume-title":"Hymba: A Hybrid-head Architecture for Small Language Models. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=A1ztozypga","author":"Dong Xin","year":"2025","unstructured":"Xin Dong, Yonggan Fu, Shizhe Diao, Wonmin Byeon, ZIJIA CHEN, Ameya Sunil Mahabaleshwarkar, Shih-Yang Liu, Matthijs Van keirsbilck, Min-Hung Chen, Yoshi Suhara, Yingyan Celine Lin, Jan Kautz, and Pavlo Molchanov. 2025. Hymba: A Hybrid-head Architecture for Small Language Models. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=A1ztozypga"},{"key":"e_1_3_2_1_23_1","first-page":"76852","article-title":"Flocks of stochastic parrots: Differentially private prompt learning for large language models","volume":"36","author":"Duan Haonan","year":"2023","unstructured":"Haonan Duan, Adam Dziedzic, Nicolas Papernot, and Franziska Boenisch. 2023. Flocks of stochastic parrots: Differentially private prompt learning for large language models. Advances in Neural Information Processing Systems, Vol. 36 (2023), 76852-76871.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.230"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCMI63661.2024.10851608"},{"key":"e_1_3_2_1_26_1","volume-title":"FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender Systems. arXiv preprint arXiv:2502.02966","author":"Fayyazi Arya","year":"2025","unstructured":"Arya Fayyazi, Mehdi Kamal, and Massoud Pedram. 2025. FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender Systems. arXiv preprint arXiv:2502.02966 (2025)."},{"key":"e_1_3_2_1_27_1","volume-title":"Practical membership inference attacks against fine-tuned large language models via self-prompt calibration. arXiv preprint arXiv:2311.06062","author":"Fu Wenjie","year":"2023","unstructured":"Wenjie Fu, Huandong Wang, Chen Gao, Guanghua Liu, Yong Li, and Tao Jiang. 2023. Practical membership inference attacks against fine-tuned large language models via self-prompt calibration. arXiv preprint arXiv:2311.06062 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"Zamba: A compact 7b ssm hybrid model. arXiv preprint arXiv:2405.16712","author":"Glorioso Paolo","year":"2024","unstructured":"Paolo Glorioso, Quentin Anthony, Yury Tokpanov, James Whittington, Jonathan Pilault, Adam Ibrahim, and Beren Millidge. 2024. Zamba: A compact 7b ssm hybrid model. arXiv preprint arXiv:2405.16712 (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"Hamish Ivison, Ian Magnusson, Yizhong Wang, et al.","author":"Groeneveld Dirk","year":"2024","unstructured":"Dirk Groeneveld, Iz Beltagy, Pete Walsh, Akshita Bhagia, Rodney Kinney, Oyvind Tafjord, Ananya Harsh Jha, Hamish Ivison, Ian Magnusson, Yizhong Wang, et al. 2024. Olmo: Accelerating the science of language models. arXiv preprint arXiv:2402.00838 (2024)."},{"key":"e_1_3_2_1_30_1","volume-title":"Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752","author":"Gu Albert","year":"2023","unstructured":"Albert Gu and Tri Dao. 2023. Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"Efficiently Modeling Long Sequences with Structured State Spaces. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=uYLFoz1vlAC","author":"Gu Albert","year":"2022","unstructured":"Albert Gu, Karan Goel, and Christopher Re. 2022. Efficiently Modeling Long Sequences with Structured State Spaces. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=uYLFoz1vlAC"},{"key":"e_1_3_2_1_32_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_1_33_1","volume-title":"Bridging the Safety Gap: A Guardrail Pipeline for Trustworthy LLM Inferences. arXiv preprint arXiv:2502.08142","author":"Han Shanshan","year":"2025","unstructured":"Shanshan Han, Salman Avestimehr, and Chaoyang He. 2025. Bridging the Safety Gap: A Guardrail Pipeline for Trustworthy LLM Inferences. arXiv preprint arXiv:2502.08142 (2025)."},{"key":"e_1_3_2_1_34_1","volume-title":"Han Jin, Yuhang Yao, Dimitris Stripelis, Zhaozhuo Xu, and Chaoyang He.","author":"Han Shanshan","year":"2024","unstructured":"Shanshan Han, Zijian Hu, Alay Dilipbhai Shah, Han Jin, Yuhang Yao, Dimitris Stripelis, Zhaozhuo Xu, and Chaoyang He. 2024. TorchOpera: A Compound AI System for LLM Safety. arXiv preprint arXiv:2406.10847 (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=sE7-XhLxHA","author":"He Pengcheng","year":"2023","unstructured":"Pengcheng He, Jianfeng Gao, and Weizhu Chen. 2023. DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=sE7-XhLxHA"},{"key":"e_1_3_2_1_36_1","volume-title":"Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)."},{"key":"e_1_3_2_1_37_1","volume-title":"LSTM can solve hard long time lag problems. Advances in neural information processing systems","author":"Hochreiter Sepp","year":"1996","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1996. LSTM can solve hard long time lag problems. Advances in neural information processing systems, Vol. 9 (1996)."},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the Forty-first International Conference on Machine Learning, ICML. https:\/\/openreview.net\/forum?id=e3Dpq3WdMv","author":"Hong Junyuan","year":"2024","unstructured":"Junyuan Hong, Jinhao Duan, Chenhui Zhang, Zhangheng Li, Chulin Xie, Kelsey Lieberman, James Diffenderfer, Brian R. Bartoldson, Ajay Kumar Jaiswal, Kaidi Xu, Bhavya Kailkhura, Dan Hendrycks, Dawn Song, Zhangyang Wang, and Bo Li. 2024. Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression. In Proceedings of the Forty-first International Conference on Machine Learning, ICML. https:\/\/openreview.net\/forum?id=e3Dpq3WdMv"},{"key":"e_1_3_2_1_39_1","volume-title":"Effects of scale on language model robustness. arXiv preprint arXiv:2407.18213","author":"Howe Nikolaus","year":"2024","unstructured":"Nikolaus Howe, Ian McKenzie, Oskar Hollinsworth, Michal Zajac, Tom Tseng, Aaron Tucker, Pierre-Luc Bacon, and Adam Gleave. 2024. Effects of scale on language model robustness. arXiv preprint arXiv:2407.18213 (2024)."},{"key":"e_1_3_2_1_40_1","volume-title":"SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection. arXiv preprint arXiv:2408.12748","author":"Hu Mengya","year":"2024","unstructured":"Mengya Hu, Rui Xu, Deren Lei, Yaxi Li, Mingyu Wang, Emily Ching, Eslam Kamal, and Alex Deng. 2024c. SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection. arXiv preprint arXiv:2408.12748 (2024)."},{"key":"e_1_3_2_1_41_1","volume-title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies. In First Conference on Language Modeling. https:\/\/openreview.net\/forum?id=3X2L2TFr0f","author":"Hu Shengding","year":"2024","unstructured":"Shengding Hu, Yuge Tu, Xu Han, Ganqu Cui, Chaoqun He, Weilin Zhao, Xiang Long, Zhi Zheng, Yewei Fang, Yuxiang Huang, Xinrong Zhang, Zhen Leng Thai, Chongyi Wang, Yuan Yao, Chenyang Zhao, Jie Zhou, Jie Cai, Zhongwu Zhai, Ning Ding, Chao Jia, Guoyang Zeng, dahai li, Zhiyuan Liu, and Maosong Sun. 2024b. MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies. In First Conference on Language Modeling. https:\/\/openreview.net\/forum?id=3X2L2TFr0f"},{"key":"e_1_3_2_1_42_1","volume-title":"I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models. arXiv preprint arXiv:2405.17849","author":"Hu Xing","year":"2024","unstructured":"Xing Hu, Yuan Chen, Dawei Yang, Sifan Zhou, Zhihang Yuan, Jiangyong Yu, and Chen Xu. 2024a. I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models. arXiv preprint arXiv:2405.17849 (2024)."},{"key":"e_1_3_2_1_43_1","volume-title":"Offset unlearning for large language models. arXiv preprint arXiv:2404.11045","author":"Huang James Y","year":"2024","unstructured":"James Y Huang, Wenxuan Zhou, Fei Wang, Fred Morstatter, Sheng Zhang, Hoifung Poon, and Muhao Chen. 2024. Offset unlearning for large language models. arXiv preprint arXiv:2404.11045 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"DP-BART for privatized text rewriting under local differential privacy. arXiv preprint arXiv:2302.07636","author":"Igamberdiev Timour","year":"2023","unstructured":"Timour Igamberdiev and Ivan Habernal. 2023. DP-BART for privatized text rewriting under local differential privacy. arXiv preprint arXiv:2302.07636 (2023)."},{"key":"e_1_3_2_1_45_1","unstructured":"Hakan Inan Kartikeya Upasani Jianfeng Chi Rashi Rungta Krithika Iyer Yuning Mao Michael Tontchev Qing Hu Brian Fuller Davide Testuggine et al. 2023. Llama guard: Llm-based input-output safeguard for human-ai conversations. arXiv preprint arXiv:2312.06674 (2023)."},{"key":"e_1_3_2_1_46_1","volume-title":"International Conference on Machine Learning. PMLR, 17506-17533","author":"Korbak Tomasz","year":"2023","unstructured":"Tomasz Korbak, Kejian Shi, Angelica Chen, Rasika Vinayak Bhalerao, Christopher Buckley, Jason Phang, Samuel R Bowman, and Ethan Perez. 2023. Pretraining language models with human preferences. In International Conference on Machine Learning. PMLR, 17506-17533."},{"key":"e_1_3_2_1_47_1","volume-title":"First Conference on Language Modeling. https:\/\/openreview.net\/forum?id=9Ik05cycLq","author":"Kumar Aounon","year":"2024","unstructured":"Aounon Kumar, Chirag Agarwal, Suraj Srinivas, Aaron Jiaxun Li, Soheil Feizi, and Himabindu Lakkaraju. 2024. Certifying LLM Safety against Adversarial Prompting. In First Conference on Language Modeling. https:\/\/openreview.net\/forum?id=9Ik05cycLq"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-industry.99"},{"key":"e_1_3_2_1_49_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. ArXiv e-prints (2016), arXiv-1607."},{"key":"e_1_3_2_1_50_1","volume-title":"Jamba: Hybrid Transformer-Mamba Language Models. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=JFPaD7lpBD","author":"Lenz Barak","year":"2025","unstructured":"Barak Lenz, Opher Lieber, Alan Arazi, Amir Bergman, Avshalom Manevich, Barak Peleg, Ben Aviram, Chen Almagor, Clara Fridman, Dan Padnos, Daniel Gissin, Daniel Jannai, Dor Muhlgay, Dor Zimberg, Edden M. Gerber, Elad Dolev, Eran Krakovsky, Erez Safahi, Erez Schwartz, Gal Cohen, Gal Shachaf, Haim Rozenblum, Hofit Bata, Ido Blass, Inbal Magar, Itay Dalmedigos, Jhonathan Osin, Julie Fadlon, Maria Rozman, Matan Danos, Michael Gokhman, Mor Zusman, Naama Gidron, Nir Ratner, Noam Gat, Noam Rozen, Oded Fried, Ohad Leshno, Omer Antverg, Omri Abend, Or Dagan, Orit Cohavi, Raz Alon, Ro'i Belson, Roi Cohen, Rom Gilad, Roman Glozman, Shahar Lev, Shai Shalev-Shwartz, Shaked Haim Meirom, Tal Delbari, Tal Ness, Tomer Asida, Tom Ben Gal, Tom Braude, Uriya Pumerantz, Josh Cohen, Yonatan Belinkov, Yuval Globerson, Yuval Peleg Levy, and Yoav Shoham. 2025. Jamba: Hybrid Transformer-Mamba Language Models. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=JFPaD7lpBD"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.269"},{"key":"e_1_3_2_1_52_1","volume-title":"Multi-step jailbreaking privacy attacks on chatgpt. arXiv preprint arXiv:2304.05197","author":"Li Haoran","year":"2023","unstructured":"Haoran Li, Dadi Guo, Wei Fan, Mingshi Xu, Jie Huang, Fanpu Meng, and Yangqiu Song. 2023a. Multi-step jailbreaking privacy attacks on chatgpt. arXiv preprint arXiv:2304.05197 (2023)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.4"},{"key":"e_1_3_2_1_54_1","first-page":"14200","article-title":"Datacomp-lm: In search of the next generation of training sets for language models","volume":"37","author":"Li Jeffrey","year":"2024","unstructured":"Jeffrey Li, Alex Fang, Georgios Smyrnis, Maor Ivgi, Matt Jordan, Samir Yitzhak Gadre, Hritik Bansal, Etash Guha, Sedrick Scott Keh, Kushal Arora, et al. 2024a. Datacomp-lm: In search of the next generation of training sets for language models. Advances in Neural Information Processing Systems, Vol. 37 (2024), 14200-14282.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.769"},{"key":"e_1_3_2_1_56_1","volume-title":"Purifying large language models by ensembling a small language model. arXiv preprint arXiv:2402.14845","author":"Li Tianlin","year":"2024","unstructured":"Tianlin Li, Qian Liu, Tianyu Pang, Chao Du, Qing Guo, Yang Liu, and Min Lin. 2024c. Purifying large language models by ensembling a small language model. arXiv preprint arXiv:2402.14845 (2024)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.291"},{"key":"e_1_3_2_1_58_1","volume-title":"How Far are LLMs from Real Search? A Comprehensive Study on Efficiency, Completeness, and Inherent Capabilities. arXiv preprint arXiv:2502.18387","author":"Lin Minhua","year":"2025","unstructured":"Minhua Lin, Hui Liu, Xianfeng Tang, Jingying Zeng, Zhenwei Dai, Chen Luo, Zheng Li, Xiang Zhang, Qi He, and Suhang Wang. 2025. How Far are LLMs from Real Search? A Comprehensive Study on Efficiency, Completeness, and Inherent Capabilities. arXiv preprint arXiv:2502.18387 (2025)."},{"key":"e_1_3_2_1_59_1","unstructured":"Aixin Liu Bei Feng Bin Wang Bingxuan Wang Bo Liu Chenggang Zhao Chengqi Dengr Chong Ruan Damai Dai Daya Guo et al. 2024a. Deepseek-v2: A strong economical and efficient mixture-of-experts language model. arXiv preprint arXiv:2405.04434 (2024)."},{"key":"e_1_3_2_1_60_1","volume-title":"Tuning language models by proxy. arXiv preprint arXiv:2401.08565","author":"Liu Alisa","year":"2024","unstructured":"Alisa Liu, Xiaochuang Han, Yizhong Wang, Yulia Tsvetkov, Yejin Choi, and Noah A Smith. 2024b. Tuning language models by proxy. arXiv preprint arXiv:2401.08565 (2024)."},{"key":"e_1_3_2_1_61_1","volume-title":"Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling. arXiv preprint arXiv:2502.06703","author":"Liu Runze","year":"2025","unstructured":"Runze Liu, Junqi Gao, Jian Zhao, Kaiyan Zhang, Xiu Li, Biqing Qi, Wanli Ouyang, and Bowen Zhou. 2025. Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling. arXiv preprint arXiv:2502.06703 (2025)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.237"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA-BDCloud-SocialCom-SustainCom51426.2020.00095"},{"key":"e_1_3_2_1_64_1","volume-title":"Mobilellm: Optimizing sub-billion parameter language models for on-device use cases. arXiv preprint arXiv:2402.14905","author":"Liu Zechun","year":"2024","unstructured":"Zechun Liu, Changsheng Zhao, Forrest Iandola, Chen Lai, Yuandong Tian, Igor Fedorov, Yunyang Xiong, Ernie Chang, Yangyang Shi, Raghuraman Krishnamoorthi, et al. 2024c. Mobilellm: Optimizing sub-billion parameter language models for on-device use cases. arXiv preprint arXiv:2402.14905 (2024)."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.179"},{"key":"e_1_3_2_1_66_1","volume-title":"Small language models: Survey, measurements, and insights. arXiv preprint arXiv:2409.15790","author":"Lu Zhenyan","year":"2024","unstructured":"Zhenyan Lu, Xiang Li, Dongqi Cai, Rongjie Yi, Fangming Liu, Xiwen Zhang, Nicholas D Lane, and Mengwei Xu. 2024. Small language models: Survey, measurements, and insights. arXiv preprint arXiv:2409.15790 (2024)."},{"key":"e_1_3_2_1_67_1","volume-title":"BioGPT: generative pre-trained transformer for biomedical text generation and mining. Briefings in bioinformatics","author":"Luo Renqian","year":"2022","unstructured":"Renqian Luo, Liai Sun, Yingce Xia, Tao Qin, Sheng Zhang, Hoifung Poon, and Tie-Yan Liu. 2022. BioGPT: generative pre-trained transformer for biomedical text generation and mining. Briefings in bioinformatics, Vol. 23, 6 (2022), bbac409."},{"key":"e_1_3_2_1_68_1","volume-title":"Oyvind Tafjord, Dustin Schwenk, Evan Pete Walsh, Yanai Elazar, Kyle Lo, et al.","author":"Magnusson Ian","year":"2023","unstructured":"Ian Magnusson, Akshita Bhagia, Valentin Hofmann, Luca Soldaini, Ananya Harsh Jha, Oyvind Tafjord, Dustin Schwenk, Evan Pete Walsh, Yanai Elazar, Kyle Lo, et al. 2023. Paloma: A benchmark for evaluating language model fit. arXiv preprint arXiv:2312.10523 (2023)."},{"key":"e_1_3_2_1_69_1","volume-title":"Workshop on Efficient Systems for Foundation Models II@ ICML2024","author":"Mehta Sachin","year":"2024","unstructured":"Sachin Mehta, Mohammad Hossein Sekhavat, Qingqing Cao, Maxwell Horton, Yanzi Jin, Chenfan Sun, Seyed Iman Mirzadeh, Mahyar Najibi, Dmitry Belenko, Peter Zatloukal, et al. 2024. Openelm: An efficient language model family with open training and inference framework. In Workshop on Efficient Systems for Foundation Models II@ ICML2024."},{"key":"e_1_3_2_1_70_1","volume-title":"Smaller language models are capable of selecting instruction-tuning training data for larger language models. arXiv preprint arXiv:2402.10430","author":"Mekala Dheeraj","year":"2024","unstructured":"Dheeraj Mekala, Alex Nguyen, and Jingbo Shang. 2024. Smaller language models are capable of selecting instruction-tuning training data for larger language models. arXiv preprint arXiv:2402.10430 (2024)."},{"key":"e_1_3_2_1_71_1","volume-title":"The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Eo7kv0sllr","author":"Mitchell Eric","year":"2024","unstructured":"Eric Mitchell, Rafael Rafailov, Archit Sharma, Chelsea Finn, and Christopher D Manning. 2024. An Emulator for Fine-tuning Large Language Models using Small Language Models. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Eo7kv0sllr"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.152"},{"key":"e_1_3_2_1_73_1","first-page":"41076","article-title":"Compact language models via pruning and knowledge distillation","volume":"37","author":"Muralidharan Saurav","year":"2024","unstructured":"Saurav Muralidharan, Sharath Turuvekere Sreenivas, Raviraj Joshi, Marcin Chochowski, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Jan Kautz, and Pavlo Molchanov. 2024. Compact language models via pruning and knowledge distillation. Advances in Neural Information Processing Systems, Vol. 37 (2024), 41076-41102.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_74_1","volume-title":"Is On-Device AI Broken and Exploitable? Assessing the Trust and Ethics in Small Language Models. arXiv preprint arXiv:2406.05364","author":"Nakka Kalyan","year":"2024","unstructured":"Kalyan Nakka, Jimmy Dani, and Nitesh Saxena. 2024. Is On-Device AI Broken and Exploitable? Assessing the Trust and Ethics in Small Language Models. arXiv preprint arXiv:2406.05364 (2024)."},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"crossref","unstructured":"Yurii Nesterov et al. 2018. Lectures on convex optimization. Vol. 137. Springer.","DOI":"10.1007\/978-3-319-91578-4_2"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP40000.2020.00095"},{"key":"e_1_3_2_1_77_1","unstructured":"Pascal Pfeiffer Philipp Singer Yauhen Babakhin Gabor Fodor Nischay Dhankhar and Sri Satish Ambati. 2024. H2O-Danube3 Technical Report. arXiv preprint arXiv:2407.09276 (2024)."},{"key":"e_1_3_2_1_78_1","volume-title":"Lightweight safety classification using pruned language models. arXiv preprint arXiv:2412.13435","author":"Sawtell Mason","year":"2024","unstructured":"Mason Sawtell, Tula Masterman, Sandi Besen, and Jim Brown. 2024. Lightweight safety classification using pruned language models. arXiv preprint arXiv:2412.13435 (2024)."},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00434"},{"key":"e_1_3_2_1_80_1","volume-title":"Neurips 2024 Workshop Foundation Models for Science: Progress, Opportunities, and Challenges. https:\/\/openreview.net\/forum?id=rn0JKIvABP","author":"Schmidinger Niklas","year":"2024","unstructured":"Niklas Schmidinger, Lisa Schneckenreiter, Philipp Seidl, Johannes Schimunek, Sohvi Luukkonen, Pieter-Jan Hoedt, Johannes Brandstetter, Andreas Mayr, Sepp Hochreiter, and G\u00fcnter Klambauer. 2024. Bio-xLS\u2122: Generative modeling, representation and in-context learning of biological and chemical sequences. In Neurips 2024 Workshop Foundation Models for Science: Progress, Opportunities, and Challenges. https:\/\/openreview.net\/forum?id=rn0JKIvABP"},{"key":"e_1_3_2_1_81_1","volume-title":"Yu Fu, Pedram Zaree, Yue Dong, and Nael Abu-Ghazaleh.","author":"Shayegani Erfan","year":"2023","unstructured":"Erfan Shayegani, Md Abdullah Al Mamun, Yu Fu, Pedram Zaree, Yue Dong, and Nael Abu-Ghazaleh. 2023. Survey of vulnerabilities in large language models revealed by adversarial attacks. arXiv preprint arXiv:2310.10844 (2023)."},{"key":"e_1_3_2_1_82_1","volume-title":"Fast transformer decoding: One write-head is all you need. arXiv preprint arXiv:1911.02150","author":"Shazeer Noam","year":"2019","unstructured":"Noam Shazeer. 2019. Fast transformer decoding: One write-head is all you need. arXiv preprint arXiv:1911.02150 (2019)."},{"key":"e_1_3_2_1_83_1","volume-title":"Glu variants improve transformer. arXiv preprint arXiv:2002.05202","author":"Shazeer Noam","year":"2020","unstructured":"Noam Shazeer. 2020. Glu variants improve transformer. arXiv preprint arXiv:2002.05202 (2020)."},{"key":"e_1_3_2_1_84_1","first-page":"48875","article-title":"Decoding-time language model alignment with multiple objectives","volume":"37","author":"Shi Ruizhe","year":"2024","unstructured":"Ruizhe Shi, Yifang Chen, Yushi Hu, Alisa Liu, Hanna Hajishirzi, Noah A Smith, and Simon S Du. 2024. Decoding-time language model alignment with multiple objectives. Advances in Neural Information Processing Systems, Vol. 37 (2024), 48875-48920.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_85_1","volume-title":"The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=4FWAwZtd2n","author":"Snell Charlie Victor","year":"2025","unstructured":"Charlie Victor Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. 2025. Scaling LLM Test-Time Compute Optimally Can be More Effective than Scaling Parameters for Reasoning. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=4FWAwZtd2n"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.746"},{"key":"e_1_3_2_1_87_1","volume-title":"Juliette Love, et al.","author":"Team Gemma","year":"2024","unstructured":"Gemma Team, Thomas Mesnard, Cassidy Hardin, Robert Dadashi, Surya Bhupatiraju, Shreya Pathak, Laurent Sifre, Morgane Rivi\u00e8re, Mihir Sanjay Kale, Juliette Love, et al. 2024a. Gemma: Open models based on gemini research and technology. arXiv preprint arXiv:2403.08295 (2024)."},{"key":"e_1_3_2_1_88_1","volume-title":"Cassidy Hardin, Surya Bhupatiraju, L\u00e9onard Hussenot, Thomas Mesnard, Bobak Shahriari, Alexandre Ram\u00e9, et al.","author":"Team Gemma","year":"2024","unstructured":"Gemma Team, Morgane Riviere, Shreya Pathak, Pier Giuseppe Sessa, Cassidy Hardin, Surya Bhupatiraju, L\u00e9onard Hussenot, Thomas Mesnard, Bobak Shahriari, Alexandre Ram\u00e9, et al. 2024b. Gemma 2: Improving open language models at a practical size. arXiv preprint arXiv:2408.00118 (2024)."},{"key":"e_1_3_2_1_89_1","unstructured":"TensorOpera Team. 2024. TensorOpera Unveils Fox Foundation Model: A Pioneering Small Language Model (SLM) for Cloud and Edge. https:\/\/blog.tensoropera.ai\/tensoropera-unveils-fox-foundation-model-a-pioneering-open-source-slm-leading-the-way-against-tech-giants\/ Accessed: 2024-6-13."},{"key":"e_1_3_2_1_90_1","volume-title":"Mobillama: Towards accurate and lightweight fully transparent gpt. arXiv preprint arXiv:2402.16840","author":"Thawakar Omkar","year":"2024","unstructured":"Omkar Thawakar, Ashmal Vayani, Salman Khan, Hisham Cholakal, Rao M Anwer, Michael Felsberg, Tim Baldwin, Eric P Xing, and Fahad Shahbaz Khan. 2024. Mobillama: Towards accurate and lightweight fully transparent gpt. arXiv preprint arXiv:2402.16840 (2024)."},{"key":"e_1_3_2_1_91_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_92_1","volume-title":"Calibrating Large Language Models Using Their Generations Only. arXiv preprint arXiv:2403.05973","author":"Ulmer Dennis","year":"2024","unstructured":"Dennis Ulmer, Martin Gubri, Hwaran Lee, Sangdoo Yun, and Seong Joon Oh. 2024. Calibrating Large Language Models Using Their Generations Only. arXiv preprint arXiv:2403.05973 (2024)."},{"key":"e_1_3_2_1_93_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.209"},{"key":"e_1_3_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-73197-7_16"},{"key":"e_1_3_2_1_96_1","volume-title":"Enhancements, Applications, Collaboration with LLMs, and Trustworthiness. arXiv preprint arXiv:2411.03350","author":"Wang Fali","year":"2024","unstructured":"Fali Wang, Zhiwei Zhang, Xianren Zhang, Zongyu Wu, Tzuhao Mo, Qiuhao Lu, Wanjing Wang, Rui Li, Junjie Xu, Xianfeng Tang, et al. 2024 e. A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness. arXiv preprint arXiv:2411.03350 (2024)."},{"key":"e_1_3_2_1_97_1","volume-title":"Malicious Use, and Mitigation Strategy. arXiv preprint arXiv:2501.09431","author":"Wang Huandong","year":"2025","unstructured":"Huandong Wang, Wenjie Fu, Yingzhou Tang, Zhilong Chen, Yuxi Huang, Jinghua Piao, Chen Gao, Fengli Xu, Tao Jiang, and Yong Li. 2025. A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy. arXiv preprint arXiv:2501.09431 (2025)."},{"key":"e_1_3_2_1_98_1","volume-title":"On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective. In ICLR 2023 Workshop on Trustworthy and Reliable Large-Scale Machine Learning Models.","author":"Wang Jindong","unstructured":"Jindong Wang, HU Xixu, Wenxin Hou, Hao Chen, Runkai Zheng, Yidong Wang, Linyi Yang, Wei Ye, Haojun Huang, Xiubo Geng, et al. [n.,d.]. On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective. In ICLR 2023 Workshop on Trustworthy and Reliable Large-Scale Machine Learning Models."},{"key":"e_1_3_2_1_99_1","volume-title":"2024 d. STAND-Guard: A Small Task-Adaptive Content Moderation Model. arXiv preprint arXiv:2411.05214","author":"Wang Minjia","year":"2024","unstructured":"Minjia Wang, Pingping Lin, Siqi Cai, Shengnan An, Shengjie Ma, Zeqi Lin, Congrui Huang, and Bixiong Xu. 2024 d. STAND-Guard: A Small Task-Adaptive Content Moderation Model. arXiv preprint arXiv:2411.05214 (2024)."},{"key":"e_1_3_2_1_100_1","volume-title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=1PL1NIMMrw","author":"Wang Xuezhi","year":"2023","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023. Self-Consistency Improves Chain of Thought Reasoning in Language Models. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=1PL1NIMMrw"},{"key":"e_1_3_2_1_101_1","first-page":"896","volume-title":"Do-Not-Answer: Evaluating Safeguards in LLMs. In Findings of the Association for Computational Linguistics: EACL 2024","author":"Wang Yuxia","year":"2024","unstructured":"Yuxia Wang, Haonan Li, Xudong Han, Preslav Nakov, and Timothy Baldwin. 2024c. Do-Not-Answer: Evaluating Safeguards in LLMs. In Findings of the Association for Computational Linguistics: EACL 2024. Association for Computational Linguistics, 896-911. https:\/\/aclanthology.org\/2024.findings-eacl.61"},{"key":"e_1_3_2_1_102_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72069-7_36"},{"key":"e_1_3_2_1_103_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.84"},{"key":"e_1_3_2_1_104_1","volume-title":"Scaling Inference Computation: Compute-Optimal Inference for Problem-Solving with Language Models. In The 4th Workshop on Mathematical Reasoning and AI at NeurIPS'24","author":"Wu Yangzhen","year":"2024","unstructured":"Yangzhen Wu, Zhiqing Sun, Shanda Li, Sean Welleck, and Yiming Yang. 2024. Scaling Inference Computation: Compute-Optimal Inference for Problem-Solving with Language Models. In The 4th Workshop on Mathematical Reasoning and AI at NeurIPS'24. https:\/\/openreview.net\/forum?id=j7DZWSc8qu"},{"key":"e_1_3_2_1_105_1","first-page":"59008","article-title":"Fine-grained human feedback gives better rewards for language model training","volume":"36","author":"Wu Zeqiu","year":"2023","unstructured":"Zeqiu Wu, Yushi Hu, Weijia Shi, Nouha Dziri, Alane Suhr, Prithviraj Ammanabrolu, Noah A Smith, Mari Ostendorf, and Hannaneh Hajishirzi. 2023. Fine-grained human feedback gives better rewards for language model training. Advances in Neural Information Processing Systems, Vol. 36 (2023), 59008-59033.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_106_1","volume-title":"Efficient adversarial training in llms with continuous attacks. arXiv preprint arXiv:2405.15589","author":"Xhonneux Sophie","year":"2024","unstructured":"Sophie Xhonneux, Alessandro Sordoni, Stephan G\u00fcnnemann, Gauthier Gidel, and Leo Schwinn. 2024. Efficient adversarial training in llms with continuous attacks. arXiv preprint arXiv:2405.15589 (2024)."},{"key":"e_1_3_2_1_107_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Xie Tinghao","year":"2025","unstructured":"Tinghao Xie, Xiangyu Qi, Yi Zeng, Yangsibo Huang, Udari Madhushani Sehwag, Kaixuan Huang, Luxi He, Boyi Wei, Dacheng Li, Ying Sheng, et al. 2025. SORRY-bench: Systematically evaluating large language model safety refusal. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_108_1","volume-title":"Self-Evaluation Guided Beam Search for Reasoning. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=Bw82hwg5Q3","author":"Xie Yuxi","year":"2023","unstructured":"Yuxi Xie, Kenji Kawaguchi, Yiran Zhao, Xu Zhao, Min-Yen Kan, Junxian He, and Qizhe Xie. 2023. Self-Evaluation Guided Beam Search for Reasoning. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=Bw82hwg5Q3"},{"key":"e_1_3_2_1_109_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00563"},{"key":"e_1_3_2_1_110_1","volume-title":"Audio xlstms: Learning self-supervised audio representations with xlstms. arXiv preprint arXiv:2408.16568","author":"Yadav Sarthak","year":"2024","unstructured":"Sarthak Yadav, Sergios Theodoridis, and Zheng-Hua Tan. 2024. Audio xlstms: Learning self-supervised audio representations with xlstms. arXiv preprint arXiv:2408.16568 (2024)."},{"key":"e_1_3_2_1_111_1","unstructured":"An Yang Baosong Yang Binyuan Hui Bo Zheng Bowen Yu Chang Zhou Chengpeng Li Chengyuan Li Dayiheng Liu Fei Huang et al. 2024c. Qwen2 technical report. arXiv preprint arXiv:2407.10671 (2024)."},{"key":"e_1_3_2_1_112_1","volume-title":"2024 d. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115","author":"Yang An","year":"2024","unstructured":"An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, et al. 2024 d. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115 (2024)."},{"key":"e_1_3_2_1_113_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.490"},{"key":"e_1_3_2_1_114_1","volume-title":"Assessing adversarial robustness of large language models: An empirical study. arXiv preprint arXiv:2405.02764","author":"Yang Zeyu","year":"2024","unstructured":"Zeyu Yang, Zhao Meng, Xiaochen Zheng, and Roger Wattenhofer. 2024b. Assessing adversarial robustness of large language models: An empirical study. arXiv preprint arXiv:2405.02764 (2024)."},{"key":"e_1_3_2_1_115_1","volume-title":"The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=fMbLszVO1H","author":"Ye Zhifan","year":"2025","unstructured":"Zhifan Ye, Kejing Xia, Yonggan Fu, Xin Dong, Jihoon Hong, Xiangchi Yuan, Shizhe Diao, Jan Kautz, Pavlo Molchanov, and Yingyan Celine Lin. 2025. LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=fMbLszVO1H"},{"key":"e_1_3_2_1_116_1","volume-title":"PhoneLM: an Efficient and Capable Small Language Model Family through Principled Pre-training. arXiv preprint arXiv:2411.05046","author":"Yi Rongjie","year":"2024","unstructured":"Rongjie Yi, Xiang Li, Weikai Xie, Zhenyan Lu, Chenghua Wang, Ao Zhou, Shangguang Wang, Xiwen Zhang, and Mengwei Xu. 2024. PhoneLM: an Efficient and Capable Small Language Model Family through Principled Pre-training. arXiv preprint arXiv:2411.05046 (2024)."},{"key":"e_1_3_2_1_117_1","volume-title":"Andre Manoel, Lukas Wutschitz, et al.","author":"Yu Da","year":"2021","unstructured":"Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi, Huseyin A Inan, Gautam Kamath, Janardhan Kulkarni, Yin Tat Lee, Andre Manoel, Lukas Wutschitz, et al. 2021. Differentially private fine-tuning of language models. arXiv preprint arXiv:2110.06500 (2021)."},{"key":"e_1_3_2_1_118_1","volume-title":"Robust LLM safeguarding via refusal feature adversarial training. arXiv preprint arXiv:2409.20089","author":"Yu Lei","year":"2024","unstructured":"Lei Yu, Virginie Do, Karen Hambardzumyan, and Nicola Cancedda. 2024. Robust LLM safeguarding via refusal feature adversarial training. arXiv preprint arXiv:2409.20089 (2024)."},{"key":"e_1_3_2_1_119_1","volume-title":"The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=MbfAK4s61A","author":"Yuan Youliang","year":"2024","unstructured":"Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, Jen tse Huang, Pinjia He, Shuming Shi, and Zhaopeng Tu. 2024. GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=MbfAK4s61A"},{"key":"e_1_3_2_1_120_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Zhang Biao","year":"2019","unstructured":"Biao Zhang and Rico Sennrich. 2019. Root mean square layer normalization. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_121_1","doi-asserted-by":"publisher","DOI":"10.1145\/3686852.3687069"},{"key":"e_1_3_2_1_122_1","volume-title":"Infer Large: Memory-Efficient LoRA Training for Large Language Models. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=s7DkcgpRxL","author":"Zhang Jun","year":"2025","unstructured":"Jun Zhang, Jue WANG, Huan Li, Lidan Shou, Ke Chen, Yang You, Guiming Xie, Xuejian Gong, and Kunlong Zhou. 2025 a. Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=s7DkcgpRxL"},{"key":"e_1_3_2_1_123_1","volume-title":"IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models. In ICLR.","author":"Zhang Shaokun","year":"2024","unstructured":"Shaokun Zhang, Xiaobo Xia, Zhaoqing Wang, Ling-Hao Chen, Jiale Liu, Qingyun Wu, and Tongliang Liu. 2024a. IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models. In ICLR."},{"key":"e_1_3_2_1_124_1","volume-title":"Training language model agents without modifying language models. arXiv e-prints","author":"Zhang Shaokun","year":"2024","unstructured":"Shaokun Zhang, Jieyu Zhang, Jiale Liu, Linxin Song, Chi Wang, Ranjay Krishna, and Qingyun Wu. 2024c. Training language model agents without modifying language models. arXiv e-prints (2024), arXiv-2402."},{"key":"e_1_3_2_1_125_1","volume-title":"2025 c. Can Small Language Models Reliably Resist Jailbreak Attacks? A Comprehensive Evaluation. arXiv preprint arXiv:2503.06519","author":"Zhang Wenhui","year":"2025","unstructured":"Wenhui Zhang, Huiyu Xu, Zhibo Wang, Zeqing He, Ziqi Zhu, and Kui Ren. 2025 c. Can Small Language Models Reliably Resist Jailbreak Attacks? A Comprehensive Evaluation. arXiv preprint arXiv:2503.06519 (2025)."},{"key":"e_1_3_2_1_126_1","unstructured":"Zhiwei Zhang Fali Wang Xiaomin Li Zongyu Wu Xianfeng Tang Hui Liu Qi He Wenpeng Yin and Suhang Wang. 2025 b. Catastrophic Failure of LLM Unlearning via Quantization. arxiv: 2410.16454 [cs.CL] https:\/\/arxiv.org\/abs\/2410.16454"},{"key":"e_1_3_2_1_127_1","volume-title":"Automatic calibration and error correction for large language models via pareto optimal self-supervision. arXiv preprint arXiv:2306.16564","author":"Zhao Theodore","year":"2023","unstructured":"Theodore Zhao, Mu Wei, J Samuel Preston, and Hoifung Poon. 2023. Automatic calibration and error correction for large language models via pareto optimal self-supervision. arXiv preprint arXiv:2306.16564 (2023)."},{"key":"e_1_3_2_1_128_1","volume-title":"Weak-to-Strong Jailbreaking on Large Language Models. In ICML 2024 Next Generation of AI Safety Workshop. https:\/\/openreview.net\/forum?id=shrX5xIHCW","author":"Zhao Xuandong","year":"2024","unstructured":"Xuandong Zhao, Xianjun Yang, Tianyu Pang, Chao Du, Lei Li, Yu-Xiang Wang, and William Yang Wang. 2024. Weak-to-Strong Jailbreaking on Large Language Models. In ICML 2024 Next Generation of AI Safety Workshop. https:\/\/openreview.net\/forum?id=shrX5xIHCW"},{"key":"e_1_3_2_1_129_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Zhou Yucheng","year":"2024","unstructured":"Yucheng Zhou, Jianbing Shen, and Yu Cheng. 2024b. Weak to strong generalization for large language models with multi-capabilities. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_130_1","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=dOJ6CqWDf1","author":"Zhou Zhanhui","year":"2024","unstructured":"Zhanhui Zhou, Zhixuan Liu, Jie Liu, Zhichen Dong, Chao Yang, and Yu Qiao. 2024a. Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=dOJ6CqWDf1"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3736563","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:01:50Z","timestamp":1777572110000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3736563"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":130,"alternative-id":["10.1145\/3711896.3736563","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3736563","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}