{"total":952,"rows":[{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879,"area":null},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916,"area":null},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819,"area":null},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802,"area":null},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797,"area":null},{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712,"area":null},{"id":"2206.05802","title":"Self-critiquing models for assisting human evaluators","created":"2022-06-12","cited_by_count":380,"area":null},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344,"area":null},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290,"area":null},{"id":"2106.03004","title":"Exploring the Limits of Out-of-Distribution Detection","created":"2021-06-06","cited_by_count":283,"area":null},{"id":"2303.00001","title":"Reward Design with Language Models","created":"2023-02-27","cited_by_count":261,"area":null},{"id":"2210.09150","title":"Prompting GPT-3 To Be Reliable","created":"2022-10-17","cited_by_count":260,"area":null},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258,"area":null},{"id":"2211.03540","title":"Measuring Progress on Scalable Oversight for Large Language Models","created":"2022-11-04","cited_by_count":225,"area":null},{"id":"2307.14324","title":"Evaluating the Moral Beliefs Encoded in LLMs","created":"2023-07-26","cited_by_count":215,"area":null},{"id":"2209.09858","title":"Extremely Simple Activation Shaping for Out-of-Distribution Detection","created":"2022-09-20","cited_by_count":212,"area":null},{"id":"2106.09022","title":"A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection","created":"2021-06-16","cited_by_count":207,"area":null},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207,"area":null},{"id":"2302.06692","title":"Guiding Pretraining in Reinforcement Learning with Large Language Models","created":"2023-02-13","cited_by_count":187,"area":null},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176,"area":null},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"area":null},{"id":"2305.13281","title":"LM vs LM: Detecting Factual Errors via Cross Examination","created":"2023-05-22","cited_by_count":156,"area":null},{"id":"2205.11275","title":"RL with KL penalties is better viewed as Bayesian inference","created":"2022-05-23","cited_by_count":135,"area":null},{"id":"2210.01790","title":"Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals","created":"2022-10-04","cited_by_count":126,"area":null},{"id":"2105.14111","title":"Goal Misgeneralization in Deep Reinforcement Learning","created":"2021-05-28","cited_by_count":123,"area":null},{"id":"2203.09168","title":"On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks","created":"2022-03-17","cited_by_count":120,"area":null},{"id":"2302.12254","title":"Change is Hard: A Closer Look at Subpopulation Shift","created":"2023-02-23","cited_by_count":120,"area":null},{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106,"area":null},{"id":"2206.13353","title":"Is Power-Seeking AI an Existential Risk?","created":"2022-06-16","cited_by_count":105,"area":null},{"id":"2206.00426","title":"Semantic Probabilistic Layers for Neuro-Symbolic Learning","created":"2022-06-01","cited_by_count":103,"area":null},{"id":"2207.07411","title":"Plex: Towards Reliability using Pretrained Large Model Extensions","created":"2022-07-15","cited_by_count":102,"area":null},{"id":"2107.07455","title":"Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks","created":"2021-07-15","cited_by_count":101,"area":null},{"id":"2107.06857","title":"Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot","created":"2021-07-14","cited_by_count":99,"area":null},{"id":"2407.04622","title":"On scalable oversight with weak LLMs judging strong LLMs","created":"2024-07-05","cited_by_count":99,"area":null},{"id":"2307.03718","title":"Frontier AI Regulation: Managing Emerging Risks to Public Safety","created":"2023-07-06","cited_by_count":98,"area":null},{"id":"2109.14285","title":"Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration","created":"2021-09-29","cited_by_count":92,"area":null},{"id":"2107.06908","title":"Understanding Failures in Out-of-Distribution Detection with Deep Generative Models","created":"2021-07-14","cited_by_count":89,"area":null},{"id":"2105.11066","title":"Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence","created":"2021-05-24","cited_by_count":84,"area":null},{"id":"2205.11140","title":"Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation","created":"2022-05-23","cited_by_count":81,"area":null},{"id":"2102.03896","title":"Consequences of Misaligned AI","created":"2021-02-07","cited_by_count":80,"area":null},{"id":"2106.02684","title":"Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs","created":"2021-06-04","cited_by_count":80,"area":null},{"id":"2109.06827","title":"Types of Out-of-Distribution Texts and How to Detect Them","created":"2021-09-14","cited_by_count":80,"area":null},{"id":"2507.11948","title":"Kevin: Multi-Turn RL for Generating CUDA Kernels","created":"2025-07-16","cited_by_count":78,"area":null},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73,"area":null},{"id":"2402.01383","title":"LLM-based NLG Evaluation: Current Status and Challenges","created":"2024-02-02","cited_by_count":73,"area":null},{"id":"2408.03943","title":"Building Machines that Learn and Think with People","created":"2024-07-22","cited_by_count":73,"area":null},{"id":"2306.00186","title":"Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2104.08812","title":"Contrastive Out-of-Distribution Detection for Pretrained Transformers","created":"2021-04-18","cited_by_count":71,"area":null},{"id":"2202.04414","title":"Agree to Disagree: Diversity through Disagreement for Better Transferability","created":"2022-02-09","cited_by_count":70,"area":null},{"id":"2204.11134","title":"Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?","created":"2022-04-23","cited_by_count":70,"area":null},{"id":"2105.01984","title":"Software Engineering for AI-Based Systems: A Survey","created":"2021-05-05","cited_by_count":69,"area":null},{"id":"2302.02914","title":"Energy-based Out-of-Distribution Detection for Graph Neural Networks","created":"2023-02-06","cited_by_count":68,"area":null},{"id":"2106.13906","title":"Compositional Reinforcement Learning from Logical Specifications","created":"2021-06-25","cited_by_count":67,"area":null},{"id":"2202.07789","title":"Safe Reinforcement Learning by Imagining the Near Future","created":"2022-02-15","cited_by_count":67,"area":null},{"id":"2510.20270","title":"ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases","created":"2025-10-23","cited_by_count":65,"area":null},{"id":"2209.11715","title":"The \"Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices","created":"2022-09-23","cited_by_count":63,"area":null},{"id":"2110.14216","title":"What Do We Mean by Generalization in Federated Learning?","created":"2021-10-27","cited_by_count":62,"area":null},{"id":"2212.05698","title":"MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations","created":"2022-12-12","cited_by_count":62,"area":null},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62,"area":null},{"id":"2404.12241","title":"Introducing v0.5 of the AI Safety Benchmark from MLCommons","created":"2024-04-18","cited_by_count":62,"area":null},{"id":"2305.02231","title":"Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation","created":"2023-05-02","cited_by_count":61,"area":null},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2205.01663","title":"Adversarial Training for High-Stakes Reliability","created":"2022-05-03","cited_by_count":60,"area":null},{"id":"2406.16254","title":"Confidence Regulation Neurons in Language Models","created":"2024-06-24","cited_by_count":57,"area":null},{"id":"2604.07729","title":"Emotion Concepts and their Function in a Large Language Model","created":"2026-04-09","cited_by_count":57,"area":null},{"id":"2112.15422","title":"Scalar reward is not enough: A response to Silver, Singh, Precup and Sutton (2021)","created":"2021-11-25","cited_by_count":55,"area":null},{"id":"2205.14140","title":"CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior","created":"2022-05-27","cited_by_count":55,"area":null},{"id":"2201.12323","title":"Describing Differences between Text Distributions with Natural Language","created":"2022-01-28","cited_by_count":54,"area":null},{"id":"2102.08898","title":"Few-shot Conformal Prediction with Auxiliary Tasks","created":"2021-02-17","cited_by_count":53,"area":null},{"id":"2411.17501","title":"The Limits of Inference Scaling Through Resampling","created":"2024-11-26","cited_by_count":53,"area":null},{"id":"2406.11675","title":"BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models","created":"2024-06-17","cited_by_count":50,"area":null},{"id":"2111.09277","title":"SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness","created":"2021-11-17","cited_by_count":49,"area":null},{"id":"2205.00403","title":"A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness","created":"2022-05-01","cited_by_count":49,"area":null},{"id":"2205.05256","title":"Evaluation Gaps in Machine Learning Practice","created":"2022-05-11","cited_by_count":49,"area":null},{"id":"2211.12717","title":"Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks","created":"2022-11-23","cited_by_count":49,"area":null},{"id":"2402.04247","title":"Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy","created":"2024-02-06","cited_by_count":49,"area":null},{"id":"2105.11982","title":"Quantifying Uncertainty in Deep Spatiotemporal Forecasting","created":"2021-05-25","cited_by_count":48,"area":null},{"id":"2106.09110","title":"Safe Reinforcement Learning Using Advantage-Based Intervention","created":"2021-06-16","cited_by_count":47,"area":null},{"id":"2306.09983","title":"Evaluating Superhuman Models with Consistency Checks","created":"2023-06-16","cited_by_count":47,"area":null},{"id":"2502.02528","title":"Why human-AI relationships need socioaffective alignment","created":"2025-02-04","cited_by_count":47,"area":null},{"id":"2203.07475","title":"Invariance in Policy Optimisation and Partial Identifiability in Reward Learning","created":"2022-03-14","cited_by_count":46,"area":null},{"id":"2409.00265","title":"Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction","created":"2024-08-30","cited_by_count":46,"area":null},{"id":"2502.02649","title":"Fully Autonomous AI Agents Should Not be Developed","created":"2025-02-04","cited_by_count":45,"area":null},{"id":"2505.11792","title":"Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modeling","created":"2025-05-17","cited_by_count":45,"area":null},{"id":"2107.01272","title":"Physics-Guided Deep Learning for Dynamical Systems: A Survey","created":"2021-07-02","cited_by_count":44,"area":null},{"id":"2107.04520","title":"Online Adaptation to Label Distribution Shift","created":"2021-07-09","cited_by_count":44,"area":null},{"id":"2111.01564","title":"MultiplexNet: Towards Fully Satisfied Logical Constraints in Neural Networks","created":"2021-11-02","cited_by_count":44,"area":null},{"id":"2310.00603","title":"Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals","created":"2023-10-01","cited_by_count":44,"area":null},{"id":"2403.04786","title":"Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models","created":"2024-03-03","cited_by_count":44,"area":null},{"id":"2308.12270","title":"Language Reward Modulation for Pretraining Reinforcement Learning","created":"2023-08-23","cited_by_count":43,"area":null},{"id":"2311.08702","title":"Debate Helps Supervise Unreliable Experts","created":"2023-11-15","cited_by_count":43,"area":null},{"id":"2209.07454","title":"A Unifying Framework for Online Optimization with Long-Term Constraints","created":"2022-09-15","cited_by_count":41,"area":null},{"id":"2212.04871","title":"Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet","created":"2022-12-09","cited_by_count":41,"area":null},{"id":"2312.17199","title":"Tractable Function-Space Variational Inference in Bayesian Neural Networks","created":"2023-12-28","cited_by_count":41,"area":null},{"id":"2211.13746","title":"Melting Pot 2.0","created":"2022-11-24","cited_by_count":40,"area":null},{"id":"2110.10486","title":"A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays","created":"2021-10-20","cited_by_count":37,"area":null},{"id":"2101.03064","title":"One-Class Classification: A Survey","created":"2021-01-08","cited_by_count":35,"area":null}],"next_cursor":"100"}