{"list":"other","total":117,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922},{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836},{"id":"2310.11324","title":"Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting","created":"2023-10-17","cited_by_count":817},{"id":"2305.14975","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","created":"2023-05-24","cited_by_count":812},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2307.13702","title":"Measuring Faithfulness in Chain-of-Thought Reasoning","created":"2023-07-17","cited_by_count":703},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"2404.13076","title":"LLM Evaluators Recognize and Favor Their Own Generations","created":"2024-04-15","cited_by_count":686},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499},{"id":"2404.13208","title":"The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions","created":"2024-04-19","cited_by_count":493},{"id":"2404.02151","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","created":"2024-04-02","cited_by_count":486},{"id":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469},{"id":"2404.01833","title":"Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack","created":"2024-04-02","cited_by_count":390},{"id":"2309.07875","title":"Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions","created":"2023-09-14","cited_by_count":387},{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387},{"id":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384},{"id":"2410.02736","title":"Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge","created":"2024-10-03","cited_by_count":368},{"id":"2412.14093","title":"Alignment faking in large language models","created":"2024-12-18","cited_by_count":360},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349},{"id":"2310.18018","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark","created":"2023-10-27","cited_by_count":348},{"id":"2404.18796","title":"Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models","created":"2024-04-29","cited_by_count":326},{"id":"2402.10669","title":"Humans or LLMs as the Judge? A Study on Judgement Biases","created":"2024-02-16","cited_by_count":323},{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322},{"id":"2410.12784","title":"JudgeBench: A Benchmark for Evaluating LLM-based Judges","created":"2024-10-16","cited_by_count":318},{"id":"2310.07641","title":"Evaluating Large Language Models at Evaluating Instruction Following","created":"2023-10-11","cited_by_count":302},{"id":"2402.01306","title":"KTO: Model Alignment as Prospect Theoretic Optimization","created":"2024-02-02","cited_by_count":264},{"id":"2406.19314","title":"LiveBench: A Challenging, Contamination-Limited LLM Benchmark","created":"2024-06-27","cited_by_count":262},{"id":"1906.01820","title":"Risks from Learned Optimization in Advanced Machine Learning Systems","created":"2019-06-05","cited_by_count":258},{"id":"2410.21819","title":"Self-Preference Bias in LLM-as-a-Judge","created":"2024-10-29","cited_by_count":258},{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243},{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238},{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231},{"id":"2306.04528","title":"PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts","created":"2023-06-07","cited_by_count":226},{"id":"2402.16822","title":"Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts","created":"2024-02-26","cited_by_count":205},{"id":"2406.12624","title":"Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges","created":"2024-06-18","cited_by_count":205},{"id":"2311.04850","title":"Rethinking Benchmark and Contamination for Language Models with Rephrased Samples","created":"2023-11-08","cited_by_count":195},{"id":"2306.04634","title":"On the Reliability of Watermarks for Large Language Models","created":"2023-06-07","cited_by_count":189},{"id":"2406.10162","title":"Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models","created":"2024-06-14","cited_by_count":178},{"id":"2410.16184","title":"RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style","created":"2024-10-21","cited_by_count":176},{"id":"2502.17424","title":"Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs","created":"2025-02-24","cited_by_count":172},{"id":"2310.05470","title":"Generative Judge for Evaluating Alignment","created":"2023-10-09","cited_by_count":169},{"id":"2403.06634","title":"Stealing Part of a Production Language Model","created":"2024-03-11","cited_by_count":159},{"id":"1803.04585","title":"Categorizing Variants of Goodhart's Law","created":"2018-03-13","cited_by_count":149},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147},{"id":"2311.07590","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","created":"2023-11-09","cited_by_count":146},{"id":"2406.13352","title":"AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents","created":"2024-06-19","cited_by_count":145},{"id":"2211.09110","title":"Holistic Evaluation of Language Models","created":"2022-11-16","cited_by_count":131},{"id":"2402.14016","title":"Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment","created":"2024-02-21","cited_by_count":126},{"id":"2511.04703","title":"Measuring what Matters: Construct Validity in Large Language Model Benchmarks","created":"2025-11-03","cited_by_count":119},{"id":"2405.15589","title":"Efficient Adversarial Training in LLMs with Continuous Attacks","created":"2024-05-24","cited_by_count":113},{"id":"2410.20266","title":"Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Tasks","created":"2024-10-26","cited_by_count":106},{"id":"2411.15287","title":"Sycophancy in Large Language Models: Causes and Mitigations","created":"2024-11-22","cited_by_count":101},{"id":"2404.10271","title":"Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback","created":"2024-04-16","cited_by_count":100},{"id":"2502.12893","title":"H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking","created":"2025-02-18","cited_by_count":99},{"id":"2410.10700","title":"LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts","created":"2024-10-14","cited_by_count":86},{"id":"2401.13138","title":"Visibility into AI Agents","created":"2024-01-23","cited_by_count":79},{"id":"2412.03556","title":"Best-of-N Jailbreaking","created":"2024-12-04","cited_by_count":76},{"id":"2306.07951","title":"Questioning the Survey Responses of Large Language Models","created":"2023-06-13","cited_by_count":74},{"id":"2407.01100","title":"Eliminating Position Bias of Language Models: A Mechanistic Approach","created":"2024-07-01","cited_by_count":65},{"id":"2502.06559","title":"Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation","created":"2025-02-10","cited_by_count":60},{"id":"2502.13295","title":"Demonstrating specification gaming in reasoning models","created":"2025-02-18","cited_by_count":56},{"id":"2410.13341","title":"Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data","created":"2024-10-17","cited_by_count":51},{"id":"2403.04893","title":"A Safe Harbor for AI Evaluation and Red Teaming","created":"2024-03-07","cited_by_count":47},{"id":"2310.16410","title":"Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero","created":"2023-10-25","cited_by_count":42},{"id":"2407.16711","title":"Benchmarks as Microscopes: A Call for Model Metrology","created":"2024-07-22","cited_by_count":35},{"id":"2502.14425","title":"A Survey on Data Contamination for Large Language Models","created":"2025-02-20","cited_by_count":35},{"id":"2602.16763","title":"When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation","created":"2026-02-18","cited_by_count":33},{"id":"2605.02964","title":"Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use","created":"2026-05-03","cited_by_count":31},{"id":"2510.04721","title":"BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs","created":"2025-10-06","cited_by_count":27},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26},{"id":"2602.01002","title":"How RLHF Amplifies Sycophancy","created":"2026-02-01","cited_by_count":23},{"id":"2602.01539","title":"MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety","created":"2026-02-02","cited_by_count":21},{"id":"1902.09469","title":"Embedded Agency","created":"2019-02-25","cited_by_count":19},{"id":"2404.14068","title":"Holistic Safety and Responsibility Evaluations of Advanced AI Models","created":"2024-04-22","cited_by_count":19},{"id":"2503.02574","title":"LLM-Safety Evaluations Lack Robustness","created":"2025-03-04","cited_by_count":18}],"next_cursor":"100"}