{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"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":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017},{"id":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"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":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2308.07201","title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","created":"2023-08-14","cited_by_count":742},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729},{"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":"2406.11939","title":"From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline","created":"2024-06-17","cited_by_count":500},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494},{"id":"2309.11998","title":"LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset","created":"2023-09-21","cited_by_count":461},{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"2303.17491","title":"Language Models can Solve Computer Tasks","created":"2023-03-30","cited_by_count":372},{"id":"2305.03047","title":"Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision","created":"2023-05-04","cited_by_count":318},{"id":"2210.08726","title":"RARR: Researching and Revising What Language Models Say, Using Language Models","created":"2022-10-17","cited_by_count":287},{"id":"2406.15513","title":"PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference","created":"2024-06-20","cited_by_count":261},{"id":"2406.01297","title":"When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs","created":"2024-06-03","cited_by_count":240},{"id":"2209.13085","title":"Defining and Characterizing Reward Hacking","created":"2022-09-27","cited_by_count":203},{"id":"2402.05749","title":"Generalized Preference Optimization: A Unified Approach to Offline Alignment","created":"2024-02-08","cited_by_count":157},{"id":"2311.14096","title":"Cultural Bias and Cultural Alignment of Large Language Models","created":"2023-11-23","cited_by_count":149},{"id":"2404.16019","title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","created":"2024-04-24","cited_by_count":144},{"id":"2406.07814","title":"Collective Constitutional AI: Aligning a Language Model with Public Input","created":"2024-06-12","cited_by_count":123},{"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":"2405.17977","title":"Aligning to Thousands of Preferences via System Message Generalization","created":"2024-05-28","cited_by_count":84},{"id":"2503.08688","title":"Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs","created":"2025-03-11","cited_by_count":54},{"id":"2406.06560","title":"Inverse Constitutional AI: Compressing Preferences into Principles","created":"2024-06-02","cited_by_count":41},{"id":"2410.06961","title":"Self-Boosting Large Language Models with Synthetic Preference Data","created":"2024-10-09","cited_by_count":40},{"id":"2405.14092","title":"Large Language Models Can Self-Correct with Key Condition Verification","created":"2024-05-23","cited_by_count":39},{"id":"2506.08123","title":"QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA","created":"2025-06-09","cited_by_count":28},{"id":"2312.06861","title":"Disentangling Perceptions of Offensiveness: Cultural and Moral Correlates","created":"2023-12-11","cited_by_count":26},{"id":"2502.10441","title":"AI Alignment at Your Discretion","created":"2025-02-10","cited_by_count":20},{"id":"2404.14313","title":"Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels","created":"2024-04-22","cited_by_count":19},{"id":"2505.21091","title":"Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)","created":"2025-05-27","cited_by_count":19},{"id":"2402.17747","title":"When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback","created":"2024-02-27","cited_by_count":17},{"id":"2502.15861","title":"C3AI: Crafting and Evaluating Constitutions for Constitutional AI","created":"2025-02-21","cited_by_count":13},{"id":"2404.09129","title":"When Hindsight is Not 20/20: Testing Limits on Reflective Thinking in Large Language Models","created":"2024-04-14","cited_by_count":12},{"id":"2505.07772","title":"The Value of Disagreement in AI Design, Evaluation, and Alignment","created":"2025-05-12","cited_by_count":12},{"id":"2411.11937","title":"Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF Datasets","created":"2024-11-18","cited_by_count":11},{"id":"2410.08820","title":"Which Demographics do LLMs Default to During Annotation?","created":"2024-10-11","cited_by_count":10},{"id":"2502.14204","title":"On-the-fly Preference Alignment via Principle-Guided Decoding","created":"2025-02-20","cited_by_count":10},{"id":"2408.02862","title":"On The Stability of Moral Preferences: A Problem with Computational Elicitation Methods","created":"2024-08-05","cited_by_count":7},{"id":"2503.09805","title":"Un-Straightening Generative AI: How Queer Artists Surface and Challenge the Normativity of Generative AI Models","created":"2025-03-12","cited_by_count":6}],"next_cursor":null}