{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:26:09Z","timestamp":1787689569103,"version":"build-2784847793"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","funder":[{"name":"NSF (National Science Foundation)","award":["III-2106758"],"award-info":[{"award-number":["III-2106758"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770854.3780302","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:07:40Z","timestamp":1785499660000},"page":"371-382","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Mining Intrinsic Rewards from LLM Hidden States for Efficient Best-of-N Sampling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0699-9164","authenticated-orcid":false,"given":"Jizhou","family":"Guo","sequence":"first","affiliation":[{"name":"Zhiyuan College, Shanghai Jiao Tong University, Shanghai, China and University of Illinois Chicago, Chicago, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6463-0031","authenticated-orcid":false,"given":"Zhaomin","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9011-0355","authenticated-orcid":false,"given":"Hanchen","family":"Yang","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3491-5968","authenticated-orcid":false,"given":"Philip S.","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Illinois Chicago, Chicago, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_2_2_1_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_2_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.68"},{"key":"e_1_3_2_2_3_1","volume-title":"Linear discriminant analysis-a brief tutorial","author":"Balakrishnama Suresh","year":"1998","unstructured":"Suresh Balakrishnama and Aravind Ganapathiraju. 1998. Linear discriminant analysis-a brief tutorial. Institute for Signal and information Processing, Vol. 18, 1998 (1998), 1-8."},{"key":"e_1_3_2_2_4_1","unstructured":"Fazl Barez Tingchen Fu Ameya Prabhu Stephen Casper Amartya Sanyal Adel Bibi Aidan O'Gara Robert Kirk Ben Bucknall Tim Fist et al. 2025. Open problems in machine unlearning for ai safety. arXiv preprint arXiv:2501.04952 (2025)."},{"key":"e_1_3_2_2_5_1","volume-title":"Discovering Latent Knowledge in Language Models Without Supervision. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ETKGuby0hcs","author":"Burns Collin","year":"2023","unstructured":"Collin Burns, Haotian Ye, Dan Klein, and Jacob Steinhardt. 2023. Discovering Latent Knowledge in Language Models Without Supervision. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ETKGuby0hcs"},{"key":"e_1_3_2_2_6_1","volume-title":"Dense reward for free in reinforcement learning from human feedback. arXiv preprint arXiv:2402.00782","author":"Chan Alex J","year":"2024","unstructured":"Alex J Chan, Hao Sun, Samuel Holt, and Mihaela Van Der Schaar. 2024. Dense reward for free in reinforcement learning from human feedback. arXiv preprint arXiv:2402.00782 (2024)."},{"key":"e_1_3_2_2_7_1","volume-title":"Training Verifiers to Solve Math Word Problems. arXiv preprint arXiv:2110.14168","author":"Cobbe Karl","year":"2021","unstructured":"Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 2021. Training Verifiers to Solve Math Word Problems. arXiv preprint arXiv:2110.14168 (2021)."},{"key":"e_1_3_2_2_8_1","volume-title":"ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback. In Forty-first International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=BOorDpKHiJ","author":"Cui Ganqu","year":"2024","unstructured":"Ganqu Cui, Lifan Yuan, Ning Ding, Guanming Yao, Bingxiang He, Wei Zhu, Yuan Ni, Guotong Xie, Ruobing Xie, Yankai Lin, Zhiyuan Liu, and Maosong Sun. 2024. ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback. In Forty-first International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=BOorDpKHiJ"},{"key":"e_1_3_2_2_9_1","volume-title":"The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=IcVSKhVpKu","author":"Dasgupta Sayantan","year":"2025","unstructured":"Sayantan Dasgupta and Trevor Cohn. 2025. Improving Language Model Distillation through Hidden State Matching. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=IcVSKhVpKu"},{"key":"e_1_3_2_2_10_1","volume-title":"A primer on the inner workings of transformer-based language models. arXiv preprint arXiv:2405.00208","author":"Ferrando Javier","year":"2024","unstructured":"Javier Ferrando, Gabriele Sarti, Arianna Bisazza, and Marta R Costa-Juss\u00e0. 2024. A primer on the inner workings of transformer-based language models. arXiv preprint arXiv:2405.00208 (2024)."},{"key":"e_1_3_2_2_11_1","volume-title":"Logits of API-Protected LLMs Leak Proprietary Information. In First Conference on Language Modeling. https:\/\/openreview.net\/forum?id=oRcYFm8vyB","author":"Finlayson Matthew","year":"2024","unstructured":"Matthew Finlayson, Xiang Ren, and Swabha Swayamdipta. 2024. Logits of API-Protected LLMs Leak Proprietary Information. In First Conference on Language Modeling. https:\/\/openreview.net\/forum?id=oRcYFm8vyB"},{"key":"e_1_3_2_2_12_1","volume-title":"Robust preference optimization through reward model distillation. arXiv preprint arXiv:2405.19316","author":"Fisch Adam","year":"2024","unstructured":"Adam Fisch, Jacob Eisenstein, Vicky Zayats, Alekh Agarwal, Ahmad Beirami, Chirag Nagpal, Pete Shaw, and Jonathan Berant. 2024. Robust preference optimization through reward model distillation. arXiv preprint arXiv:2405.19316 (2024)."},{"key":"e_1_3_2_2_13_1","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_2_14_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025b. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_2_15_1","volume-title":"Yu","author":"Guo Jizhou","year":"2025","unstructured":"Jizhou Guo, Zhaomin Wu, Hanchen Yang, and Philip S. Yu. 2025a. Mining Intrinsic Rewards from LLM Hidden States for Efficient Best-of-N Sampling. arXiv:2505.12225 [cs.LG] https:\/\/arxiv.org\/abs\/2505.12225"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-59497-3_175"},{"key":"e_1_3_2_2_17_1","unstructured":"Dan Hendrycks Collin Burns Saurav Kadavath Akul Arora Steven Basart Eric Tang Dawn Song and Jacob Steinhardt. 2021. Measuring Mathematical Problem Solving With the MATH Dataset. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2). https:\/\/openreview.net\/forum?id=7Bywt2mQsCe"},{"key":"e_1_3_2_2_18_1","unstructured":"Imbue Team. 2024. Sanitized open-source datasets for natural language and code understanding: how we evaluated our 70B model. https:\/\/imbue.com\/research\/70b-evals\/."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1544"},{"key":"e_1_3_2_2_20_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)."},{"key":"e_1_3_2_2_21_1","first-page":"1755","volume-title":"RewardBench: Evaluating Reward Models for Language Modeling. In Findings of the Association for Computational Linguistics: NAACL 2025","author":"Lambert Nathan","year":"2025","unstructured":"Nathan Lambert, Valentina Pyatkin, Jacob Morrison, Lester James Validad Miranda, Bill Yuchen Lin, Khyathi Chandu, Nouha Dziri, Sachin Kumar, Tom Zick, Yejin Choi, Noah A. Smith, and Hannaneh Hajishirzi. 2025. RewardBench: Evaluating Reward Models for Language Modeling. In Findings of the Association for Computational Linguistics: NAACL 2025, Luis Chiruzzo, Alan Ritter, and Lu Wang (Eds.). Association for Computational Linguistics, Albuquerque, New Mexico, 1755-1797. https:\/\/aclanthology.org\/2025.findings-naacl.96\/"},{"key":"e_1_3_2_2_22_1","volume-title":"Emergent world representations: Exploring a sequence model trained on a synthetic task. ICLR","author":"Li Kenneth","year":"2023","unstructured":"Kenneth Li, Aspen K Hopkins, David Bau, Fernanda Vi\u00e9gas, Hanspeter Pfister, and Martin Wattenberg. 2023. Emergent world representations: Exploring a sequence model trained on a synthetic task. ICLR (2023)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1015"},{"key":"e_1_3_2_2_24_1","volume-title":"Skywork-reward: Bag of tricks for reward modeling in llms. arXiv preprint arXiv:2410.18451","author":"Liu Chris Yuhao","year":"2024","unstructured":"Chris Yuhao Liu, Liang Zeng, Jiacai Liu, Rui Yan, Jujie He, Chaojie Wang, Shuicheng Yan, Yang Liu, and Yahui Zhou. 2024. Skywork-reward: Bag of tricks for reward modeling in llms. arXiv preprint arXiv:2410.18451 (2024)."},{"key":"e_1_3_2_2_25_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_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599931"},{"key":"e_1_3_2_2_27_1","volume-title":"Decoupled Weight Decay Regularization. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Bkg6RiCqY7","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"e_1_3_2_2_28_1","volume-title":"Raluca Ada Popa, and Ion Stoica.","author":"Luo Michael","year":"2025","unstructured":"Michael Luo, Sijun Tan, Justin Wong, Xiaoxiang Shi, William Y. Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Li Erran Li, Raluca Ada Popa, and Ion Stoica. 2025. DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL. https:\/\/pretty-radio-b75.notion.site\/DeepScaleR-Surpassing-O1-Preview-with-a-1-5B-Model-by-Scaling-RL-19681902c1468005bed8ca303013a4e2. Notion Blog."},{"key":"e_1_3_2_2_29_1","volume-title":"Locating and editing factual associations in gpt. Advances in neural information processing systems","author":"Meng Kevin","year":"2022","unstructured":"Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2022. Locating and editing factual associations in gpt. Advances in neural information processing systems, Vol. 35 (2022), 17359-17372."},{"key":"e_1_3_2_2_30_1","unstructured":"Meta. 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\/."},{"key":"e_1_3_2_2_31_1","unstructured":"Mistral AI. 2024. Introducing the world's best edge models. https:\/\/mistral.ai\/news\/ministraux."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599411"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.511"},{"key":"e_1_3_2_2_34_1","unstructured":"OpenAI. 2023a. GPT-3.5 Turbo. https:\/\/platform.openai.com\/docs\/models\/gpt-3.5-turbo."},{"key":"e_1_3_2_2_35_1","unstructured":"OpenAI. 2023b. Using logprobs. https:\/\/cookbook.openai.com\/examples\/using_logprobs."},{"key":"e_1_3_2_2_36_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al., 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_37_1","volume-title":"Scikit-learn: Machine learning in Python. the Journal of machine Learning research","author":"Pedregosa Fabian","year":"2011","unstructured":"Fabian Pedregosa, Ga\u00ebl Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, et al., 2011. Scikit-learn: Machine learning in Python. the Journal of machine Learning research, Vol. 12 (2011), 2825-2830."},{"key":"e_1_3_2_2_38_1","volume-title":"First Conference on Language Modeling. https:\/\/openreview.net\/forum?id=kEVcNxtqXk","author":"Rafailov Rafael","year":"2024","unstructured":"Rafael Rafailov, Joey Hejna, Ryan Park, and Chelsea Finn. 2024. From $r$ to $Qtextasciicircum*$: Your Language Model is Secretly a Q-Function. In First Conference on Language Modeling. https:\/\/openreview.net\/forum?id=kEVcNxtqXk"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"key":"e_1_3_2_2_40_1","volume-title":"Andrea Caponnetto, Michele Piana, and Alessandro Verri.","author":"Rosasco Lorenzo","year":"2004","unstructured":"Lorenzo Rosasco, Ernesto De Vito, Andrea Caponnetto, Michele Piana, and Alessandro Verri. 2004. Are loss functions all the same? Neural computation, Vol. 16, 5 (2004), 1063-1076."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599815"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599927"},{"key":"e_1_3_2_2_43_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_2_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.510"},{"key":"e_1_3_2_2_45_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al., 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, Vol. 35 (2022), 24824-24837."},{"key":"e_1_3_2_2_46_1","volume-title":"Principal component analysis. Chemometrics and intelligent laboratory systems","author":"Wold Svante","year":"1987","unstructured":"Svante Wold, Kim Esbensen, and Paul Geladi. 1987. Principal component analysis. Chemometrics and intelligent laboratory systems, Vol. 2, 1-3 (1987), 37-52."},{"key":"e_1_3_2_2_47_1","volume-title":"Model-Based Differentially Private Knowledge Transfer for Large Language Models. arXiv preprint arXiv:2410.10481","author":"Wu Zhaomin","year":"2024","unstructured":"Zhaomin Wu, Jizhou Guo, Junyi Hou, Bingsheng He, Lixin Fan, and Qiang Yang. 2024. Model-Based Differentially Private Knowledge Transfer for Large Language Models. arXiv preprint arXiv:2410.10481 (2024)."},{"key":"e_1_3_2_2_48_1","volume-title":"Calibrating Reasoning in Language Models with Internal Consistency. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=udZKVMPf3S","author":"Xie Zhihui","year":"2024","unstructured":"Zhihui Xie, Jizhou Guo, Tong Yu, and Shuai Li. 2024. Calibrating Reasoning in Language Models with Internal Consistency. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=udZKVMPf3S"},{"key":"e_1_3_2_2_49_1","unstructured":"Wei Xiong Hanning Zhang Nan Jiang and Tong Zhang. 2024. An Implementation of Generative PRM. https:\/\/github.com\/RLHFlow\/RLHF-Reward-Modeling."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645363"},{"key":"e_1_3_2_2_51_1","volume-title":"On early stopping in gradient descent learning. Constructive approximation","author":"Yao Yuan","year":"2007","unstructured":"Yuan Yao, Lorenzo Rosasco, and Andrea Caponnetto. 2007. On early stopping in gradient descent learning. Constructive approximation, Vol. 26, 2 (2007), 289-315."},{"key":"e_1_3_2_2_52_1","volume-title":"AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea. arXiv preprint arXiv:2411.15738","author":"Yu Qifan","year":"2024","unstructured":"Qifan Yu, Wei Chow, Zhongqi Yue, Kaihang Pan, Yang Wu, Xiaoyang Wan, Juncheng Li, Siliang Tang, Hanwang Zhang, and Yueting Zhuang. 2024. AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea. arXiv preprint arXiv:2411.15738 (2024)."},{"key":"e_1_3_2_2_53_1","volume-title":"Advancing LLM Reasoning Generalists with Preference Trees. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=2ea5TNVR0c","author":"Yuan Lifan","year":"2025","unstructured":"Lifan Yuan, Ganqu Cui, Hanbin Wang, Ning Ding, Xingyao Wang, Boji Shan, Zeyuan Liu, Jia Deng, Huimin Chen, Ruobing Xie, Yankai Lin, Zhenghao Liu, Bowen Zhou, Hao Peng, Zhiyuan Liu, and Maosong Sun. 2025. Advancing LLM Reasoning Generalists with Preference Trees. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=2ea5TNVR0c"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1472"},{"key":"e_1_3_2_2_55_1","volume-title":"Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification. arXiv preprint arXiv:2504.05419","author":"Zhang Anqi","year":"2025","unstructured":"Anqi Zhang, Yulin Chen, Jane Pan, Chen Zhao, Aurojit Panda, Jinyang Li, and He He. 2025. Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification. arXiv preprint arXiv:2504.05419 (2025)."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599832"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2596"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657788"},{"key":"e_1_3_2_2_59_1","volume-title":"First Conference on Language Modeling. https:\/\/openreview.net\/forum?id=GqDntYTTbk","author":"Zhu Banghua","year":"2024","unstructured":"Banghua Zhu, Evan Frick, Tianhao Wu, Hanlin Zhu, Karthik Ganesan, Wei-Lin Chiang, Jian Zhang, and Jiantao Jiao. 2024. Starling-7B: Improving Helpfulness and Harmlessness with RLAIF. In First Conference on Language Modeling. https:\/\/openreview.net\/forum?id=GqDntYTTbk"},{"key":"e_1_3_2_2_60_1","unstructured":"Andy Zou Long Phan Sarah Chen James Campbell Phillip Guo Richard Ren Alexander Pan Xuwang Yin Mantas Mazeika Ann-Kathrin Dombrowski et al. 2023. Representation engineering: A top-down approach to ai transparency. arXiv preprint arXiv:2310.01405 (2023)."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3780302","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:12:16Z","timestamp":1787688736000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770854.3780302"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":60,"alternative-id":["10.1145\/3770854.3780302","10.1145\/3770854"],"URL":"https:\/\/doi.org\/10.1145\/3770854.3780302","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}