{"total":210,"rows":[{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720,"area":"alignment"},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512,"area":null},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807,"area":"lr"},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839,"area":"mechinterp"},{"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,"area":"alignment"},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437,"area":null},{"id":"2303.03846","title":"Larger language models do in-context learning differently","created":"2023-03-07","cited_by_count":394,"area":null},{"id":"2306.13213","title":"Visual Adversarial Examples Jailbreak Aligned Large Language Models","created":"2023-06-22","cited_by_count":328,"area":"mllm"},{"id":"2306.15447","title":"Are aligned neural networks adversarially aligned?","created":"2023-06-26","cited_by_count":315,"area":"alignment"},{"id":"2302.05733","title":"Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks","created":"2023-02-11","cited_by_count":278,"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":"2204.02329","title":"Can language models learn from explanations in context?","created":"2022-04-05","cited_by_count":249,"area":null},{"id":"2205.10343","title":"Towards Understanding Grokking: An Effective Theory of Representation Learning","created":"2022-05-20","cited_by_count":230,"area":null},{"id":"2402.11753","title":"ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs","created":"2024-02-19","cited_by_count":216,"area":"safety"},{"id":"2306.09479","title":"Inverse Scaling: When Bigger Isn't Better","created":"2023-06-15","cited_by_count":207,"area":null},{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205,"area":"agents"},{"id":"2305.15324","title":"Model evaluation for extreme risks","created":"2023-05-24","cited_by_count":177,"area":null},{"id":"2207.07051","title":"Language models show human-like content effects on reasoning tasks","created":"2022-07-14","cited_by_count":173,"area":"lr"},{"id":"2302.07459","title":"The Capacity for Moral Self-Correction in Large Language Models","created":"2023-02-15","cited_by_count":173,"area":"alignment"},{"id":"2310.12921","title":"Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning","created":"2023-10-19","cited_by_count":165,"area":"mllm"},{"id":"2205.10487","title":"Scaling Laws and Interpretability of Learning from Repeated Data","created":"2022-05-21","cited_by_count":152,"area":null},{"id":"2205.10782","title":"Instruction Induction: From Few Examples to Natural Language Task Descriptions","created":"2022-05-22","cited_by_count":152,"area":null},{"id":"2304.11158","title":"Emergent and Predictable Memorization in Large Language Models","created":"2023-04-21","cited_by_count":148,"area":null},{"id":"2310.02304","title":"Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation","created":"2023-10-03","cited_by_count":148,"area":"synth"},{"id":"2302.03025","title":"A Toy Model of Universality: Reverse Engineering How Networks Learn Group Operations","created":"2023-02-06","cited_by_count":144,"area":"mechinterp"},{"id":"2309.00667","title":"Taken out of context: On measuring situational awareness in LLMs","created":"2023-09-01","cited_by_count":143,"area":null},{"id":"2303.13506","title":"The Quantization Model of Neural Scaling","created":"2023-03-23","cited_by_count":138,"area":null},{"id":"2302.08500","title":"Auditing large language models: a three-layered approach","created":"2023-02-16","cited_by_count":137,"area":null},{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135,"area":"agents"},{"id":"2306.01941","title":"AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap","created":"2023-06-02","cited_by_count":123,"area":null},{"id":"2303.15715","title":"Foundation Models and Fair Use","created":"2023-03-28","cited_by_count":116,"area":null},{"id":"2307.15936","title":"A Theory for Emergence of Complex Skills in Language Models","created":"2023-07-29","cited_by_count":113,"area":null},{"id":"2210.14891","title":"Broken Neural Scaling Laws","created":"2022-10-26","cited_by_count":109,"area":null},{"id":"2302.02337","title":"Regulating ChatGPT and other Large Generative AI Models","created":"2023-02-05","cited_by_count":104,"area":null},{"id":"2311.09807","title":"The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text","created":"2023-11-16","cited_by_count":100,"area":null},{"id":"2406.04836","title":"Revisiting Catastrophic Forgetting in Large Language Model Tuning","created":"2024-06-07","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":"2403.15796","title":"Understanding Emergent Abilities of Language Models from the Loss Perspective","created":"2024-03-23","cited_by_count":94,"area":null},{"id":"2210.15424","title":"What Language Model to Train if You Have One Million GPU Hours?","created":"2022-10-27","cited_by_count":92,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2212.09803","title":"Training Trajectories of Language Models Across Scales","created":"2022-12-19","cited_by_count":81,"area":null},{"id":"2311.09827","title":"Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking","created":"2023-11-16","cited_by_count":81,"area":"lr"},{"id":"2401.13138","title":"Visibility into AI Agents","created":"2024-01-23","cited_by_count":79,"area":null},{"id":"2211.02011","title":"Inverse scaling can become U-shaped","created":"2022-11-03","cited_by_count":76,"area":null},{"id":"2309.16575","title":"A Benchmark for Learning to Translate a New Language from One Grammar Book","created":"2023-09-28","cited_by_count":75,"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":"2406.18682","title":"The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm","created":"2024-06-26","cited_by_count":70,"area":"safety"},{"id":"2401.00736","title":"Diffusion Models, Image Super-Resolution And Everything: A Survey","created":"2024-01-01","cited_by_count":64,"area":"diffusion"},{"id":"2206.05862","title":"X-Risk Analysis for AI Research","created":"2022-06-13","cited_by_count":60,"area":null},{"id":"2210.11399","title":"Transcending Scaling Laws with 0.1% Extra Compute","created":"2022-10-20","cited_by_count":57,"area":null},{"id":"2405.11751","title":"Asymptotic theory of in-context learning by linear attention","created":"2024-05-20","cited_by_count":55,"area":null},{"id":"2312.10523","title":"Paloma: A Benchmark for Evaluating Language Model Fit","created":"2023-12-16","cited_by_count":54,"area":null},{"id":"2311.17391","title":"Unveiling the Implicit Toxicity in Large Language Models","created":"2023-11-29","cited_by_count":51,"area":null},{"id":"2310.17688","title":"Managing extreme AI risks amid rapid progress","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2412.09764","title":"Memory Layers at Scale","created":"2024-12-12","cited_by_count":48,"area":null},{"id":"2306.09983","title":"Evaluating Superhuman Models with Consistency Checks","created":"2023-06-16","cited_by_count":47,"area":null},{"id":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2311.01967","title":"The language of prompting: What linguistic properties make a prompt successful?","created":"2023-11-03","cited_by_count":44,"area":null},{"id":"2402.14433","title":"A Language Model's Guide Through Latent Space","created":"2024-02-22","cited_by_count":43,"area":null},{"id":"2502.17578","title":"How Do Large Language Monkeys Get Their Power (Laws)?","created":"2025-02-24","cited_by_count":43,"area":"safety"},{"id":"2205.05789","title":"RITA: a Study on Scaling Up Generative Protein Sequence Models","created":"2022-05-11","cited_by_count":42,"area":null},{"id":"2306.11932","title":"Opportunities and Risks of LLMs for Scalable Deliberation with Polis","created":"2023-06-20","cited_by_count":42,"area":null},{"id":"2312.03801","title":"Generalization to New Sequential Decision Making Tasks with In-Context Learning","created":"2023-12-06","cited_by_count":39,"area":null},{"id":"2406.00048","title":"Towards a theory of how the structure of language is acquired by deep neural networks","created":"2024-05-28","cited_by_count":39,"area":null},{"id":"2502.16534","title":"Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs","created":"2025-02-23","cited_by_count":39,"area":null},{"id":"2401.04757","title":"How predictable is language model benchmark performance?","created":"2024-01-09","cited_by_count":37,"area":null},{"id":"2503.05788","title":"Emergent Abilities in Large Language Models: A Survey","created":"2025-02-28","cited_by_count":37,"area":null},{"id":"2306.07377","title":"Lost in Translation: Large Language Models in Non-English Content Analysis","created":"2023-06-12","cited_by_count":35,"area":null},{"id":"2308.15419","title":"Characterizing Learning Curves During Language Model Pre-Training: Learning, Forgetting, and Stability","created":"2023-08-29","cited_by_count":35,"area":null},{"id":"2509.23024","title":"Tracing the Representation Geometry of Language Models from Pretraining to Post-training","created":"2025-09-27","cited_by_count":35,"area":null},{"id":"2305.14947","title":"How Predictable Are Large Language Model Capabilities? A Case Study on BIG-bench","created":"2023-05-24","cited_by_count":34,"area":null},{"id":"2407.07890","title":"Training on the Test Task Confounds Evaluation and Emergence","created":"2024-07-10","cited_by_count":34,"area":null},{"id":"2411.03336","title":"Towards evaluations-based safety cases for AI scheming","created":"2024-10-29","cited_by_count":33,"area":null},{"id":"2310.05292","title":"How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debugging","created":"2023-10-08","cited_by_count":30,"area":"agents"},{"id":"2402.06475","title":"Large Language Models for Captioning and Retrieving Remote Sensing Images","created":"2024-02-09","cited_by_count":30,"area":null},{"id":"2504.01550","title":"Representation Bending for Large Language Model Safety","created":"2025-04-02","cited_by_count":30,"area":"safety"},{"id":"2310.03262","title":"Predicting Emergent Abilities with Infinite Resolution Evaluation","created":"2023-10-05","cited_by_count":28,"area":null},{"id":"2402.15350","title":"Farsight: Fostering Responsible AI Awareness During AI Application Prototyping","created":"2024-02-23","cited_by_count":28,"area":null},{"id":"2505.17799","title":"A Coreset Selection of Coreset Selection Literature: Introduction and Recent Advances","created":"2025-05-23","cited_by_count":28,"area":null},{"id":"2304.03728","title":"Interpretable Unified Language Checking","created":"2023-04-07","cited_by_count":26,"area":null},{"id":"2505.17863","title":"The emergence of sparse attention: impact of data distribution and benefits of repetition","created":"2025-05-23","cited_by_count":25,"area":null},{"id":"2210.03858","title":"AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models","created":"2022-10-08","cited_by_count":23,"area":null},{"id":"2306.16244","title":"CBBQ: A Chinese Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models","created":"2023-06-28","cited_by_count":23,"area":null},{"id":"2403.03881","title":"Unlocking Dataset Distillation with Diffusion Models","created":"2024-03-06","cited_by_count":23,"area":"diffusion"},{"id":"2211.02069","title":"LMentry: A Language Model Benchmark of Elementary Language Tasks","created":"2022-11-03","cited_by_count":22,"area":null},{"id":"2311.12997","title":"Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks","created":"2023-11-21","cited_by_count":22,"area":null},{"id":"2303.11341","title":"What does it take to catch a Chinchilla? Verifying Rules on Large-Scale Neural Network Training via Compute Monitoring","created":"2023-03-20","cited_by_count":21,"area":null},{"id":"2401.07348","title":"Generative AI in EU Law: Liability, Privacy, Intellectual Property, and Cybersecurity","created":"2024-01-14","cited_by_count":21,"area":null},{"id":"2401.02452","title":"The Compute Divide in Machine Learning: A Threat to Academic Contribution and Scrutiny?","created":"2024-01-04","cited_by_count":20,"area":null},{"id":"2406.19097","title":"Fairness and Bias in Multimodal AI: A Survey","created":"2024-06-27","cited_by_count":20,"area":"mllm"},{"id":"2304.01994","title":"Waving Goodbye to Low-Res: A Diffusion-Wavelet Approach for Image Super-Resolution","created":"2023-04-04","cited_by_count":19,"area":"diffusion"},{"id":"2405.03146","title":"Quantifying the Capabilities of LLMs across Scale and Precision","created":"2024-05-06","cited_by_count":19,"area":null},{"id":"2308.06294","title":"Enhancing Phenotype Recognition in Clinical Notes Using Large Language Models: PhenoBCBERT and PhenoGPT","created":"2023-08-11","cited_by_count":18,"area":null},{"id":"2402.07179","title":"Prompt Perturbation in Retrieval-Augmented Generation based Large Language Models","created":"2024-02-11","cited_by_count":18,"area":"rag"},{"id":"2402.18502","title":"Few-Shot Fairness: Unveiling LLM's Potential for Fairness-Aware Classification","created":"2024-02-28","cited_by_count":18,"area":null},{"id":"2303.09377","title":"Protecting Society from AI Misuse: When are Restrictions on Capabilities Warranted?","created":"2023-03-16","cited_by_count":16,"area":null},{"id":"2409.02257","title":"MMLU-Pro+: Evaluating Higher-Order Reasoning and Shortcut Learning in LLMs","created":"2024-09-03","cited_by_count":16,"area":"lr"},{"id":"2310.14607","title":"Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classifications","created":"2023-10-23","cited_by_count":15,"area":"lr"},{"id":"2407.01505","title":"Self-Cognition in Large Language Models: An Exploratory Study","created":"2024-07-01","cited_by_count":15,"area":null},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"}],"next_cursor":"100"}