{"list":"other","total":62,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"2309.00267","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","created":"2023-09-01","cited_by_count":625},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"1703.00810","title":"Opening the Black Box of Deep Neural Networks via Information","created":"2017-03-02","cited_by_count":503},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328},{"id":"1707.09564","title":"A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks","created":"2017-07-29","cited_by_count":314},{"id":"1705.07809","title":"Information-theoretic analysis of generalization capability of learning algorithms","created":"2017-05-22","cited_by_count":303},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258},{"id":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184},{"id":"2309.06256","title":"Mitigating the Alignment Tax of RLHF","created":"2023-09-12","cited_by_count":183},{"id":"2406.02900","title":"Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms","created":"2024-06-05","cited_by_count":143},{"id":"2105.14111","title":"Goal Misgeneralization in Deep Reinforcement Learning","created":"2021-05-28","cited_by_count":123},{"id":"1908.04734","title":"Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective","created":"2019-08-13","cited_by_count":108},{"id":"2411.01111","title":"Rule Based Rewards for Language Model Safety","created":"2024-11-02","cited_by_count":108},{"id":"2402.19085","title":"Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment","created":"2024-02-29","cited_by_count":107},{"id":"1810.00821","title":"Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow","created":"2018-10-01","cited_by_count":105},{"id":"1511.05219","title":"How much does your data exploration overfit? Controlling bias via information usage","created":"2015-11-16","cited_by_count":95},{"id":"2305.18887","title":"How Does Information Bottleneck Help Deep Learning?","created":"2023-05-30","cited_by_count":93},{"id":"2402.09345","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling","created":"2024-02-14","cited_by_count":79},{"id":"2304.09355","title":"To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review","created":"2023-04-19","cited_by_count":72},{"id":"1705.02436","title":"Nonlinear Information Bottleneck","created":"2017-05-06","cited_by_count":71},{"id":"2312.17173","title":"Non-Vacuous Generalization Bounds for Large Language Models","created":"2023-12-28","cited_by_count":53},{"id":"2405.14758","title":"Axioms for AI Alignment from Human Feedback","created":"2024-05-23","cited_by_count":52},{"id":"2105.06948","title":"People construct simplified mental representations to plan","created":"2021-05-14","cited_by_count":47},{"id":"2409.03650","title":"On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization","created":"2024-09-05","cited_by_count":27},{"id":"2303.00633","title":"An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization","created":"2023-03-01","cited_by_count":25},{"id":"2101.06197","title":"Deciding What to Learn: A Rate-Distortion Approach","created":"2021-01-15","cited_by_count":23},{"id":"2109.04083","title":"User Tampering in Reinforcement Learning Recommender Systems","created":"2021-09-09","cited_by_count":23},{"id":"2406.05883","title":"Information Theoretic Guarantees For Policy Alignment In Large Language Models","created":"2024-06-09","cited_by_count":23},{"id":"2109.00127","title":"Cognitive science as a source of forward and inverse models of human decisions for robotics and control","created":"2021-09-01","cited_by_count":22},{"id":"2005.06641","title":"A Rate-Distortion view of human pragmatic reasoning","created":"2020-05-13","cited_by_count":19},{"id":"2206.02072","title":"Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning","created":"2022-06-04","cited_by_count":19},{"id":"2306.12214","title":"More PAC-Bayes bounds: From bounded losses, to losses with general tail behaviors, to anytime validity","created":"2023-06-21","cited_by_count":17},{"id":"2110.13973","title":"The Value of Information When Deciding What to Learn","created":"2021-10-26","cited_by_count":15},{"id":"2503.18130","title":"Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization","created":"2025-03-23","cited_by_count":14},{"id":"2401.08672","title":"Concept Alignment","created":"2024-01-09","cited_by_count":10},{"id":"2404.03176","title":"Information-Theoretic Generalization Bounds for Deep Neural Networks","created":"2024-04-04","cited_by_count":10},{"id":"2503.05728","title":"Political Neutrality in AI Is Impossible- But Here Is How to Approximate It","created":"2025-02-18","cited_by_count":10},{"id":"2208.03848","title":"Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimality","created":"2022-08-08","cited_by_count":9},{"id":"2002.05769","title":"The Efficiency of Human Cognition Reflects Planned Information Processing","created":"2020-02-13","cited_by_count":6},{"id":"2509.05381","title":"Murphys Laws of AI Alignment: Why the Gap Always Wins","created":"2025-09-04","cited_by_count":5},{"id":"1904.03964","title":"Bounded rational decision-making from elementary computations that reduce uncertainty","created":"2019-04-08","cited_by_count":4},{"id":"2305.03263","title":"Bayesian Reinforcement Learning with Limited Cognitive Load","created":"2023-05-05","cited_by_count":4},{"id":"2405.14681","title":"Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss","created":"2024-05-23","cited_by_count":4},{"id":"2503.08231","title":"How good is PAC-Bayes at explaining generalisation?","created":"2025-03-11","cited_by_count":4},{"id":"2410.13577","title":"Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks","created":"2024-10-17","cited_by_count":3},{"id":"2505.19327","title":"Paying Alignment Tax with Contrastive Learning","created":"2025-05-25","cited_by_count":3}],"next_cursor":null}