{"total":723,"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":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104,"area":"alignment"},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055,"area":"alignment"},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902,"area":null},{"id":"2305.01937","title":"Can Large Language Models Be an Alternative to Human Evaluations?","created":"2023-05-03","cited_by_count":734,"area":null},{"id":"2312.02119","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","created":"2023-12-04","cited_by_count":672,"area":"safety"},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553,"area":"mechinterp"},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531,"area":"agents"},{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509,"area":"safety"},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"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":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401,"area":null},{"id":"2106.13219","title":"Towards Understanding and Mitigating Social Biases in Language Models","created":"2021-06-24","cited_by_count":296,"area":null},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2304.08247","title":"MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data","created":"2023-04-14","cited_by_count":286,"area":null},{"id":"2112.10668","title":"Few-shot Learning with Multilingual Language Models","created":"2021-12-20","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":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2404.16789","title":"Continual Learning of Large Language Models: A Comprehensive Survey","created":"2024-04-25","cited_by_count":234,"area":null},{"id":"2308.09662","title":"Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment","created":"2023-08-18","cited_by_count":223,"area":"safety"},{"id":"2409.00920","title":"ToolACE: Winning the Points of LLM Function Calling","created":"2024-09-02","cited_by_count":216,"area":"agents"},{"id":"2307.14324","title":"Evaluating the Moral Beliefs Encoded in LLMs","created":"2023-07-26","cited_by_count":215,"area":null},{"id":"2104.08671","title":"When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset","created":"2021-04-18","cited_by_count":201,"area":null},{"id":"2309.07045","title":"SafetyBench: Evaluating the Safety of Large Language Models","created":"2023-09-13","cited_by_count":199,"area":null},{"id":"2308.14752","title":"AI Deception: A Survey of Examples, Risks, and Potential Solutions","created":"2023-08-28","cited_by_count":188,"area":null},{"id":"2305.18365","title":"What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks","created":"2023-05-27","cited_by_count":185,"area":null},{"id":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184,"area":"alignment"},{"id":"2304.03279","title":"Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark","created":"2023-04-06","cited_by_count":182,"area":null},{"id":"2103.11790","title":"Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do","created":"2021-03-08","cited_by_count":178,"area":null},{"id":"2405.13576","title":"FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research","created":"2024-05-22","cited_by_count":166,"area":"mllm"},{"id":"2311.07689","title":"MART: Improving LLM Safety with Multi-round Automatic Red-Teaming","created":"2023-11-13","cited_by_count":163,"area":"safety"},{"id":"2402.16786","title":"Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models","created":"2024-02-26","cited_by_count":162,"area":null},{"id":"2203.13722","title":"Probing Pre-Trained Language Models for Cross-Cultural Differences in Values","created":"2022-03-25","cited_by_count":149,"area":null},{"id":"2309.00363","title":"FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning","created":"2023-09-01","cited_by_count":149,"area":null},{"id":"2110.07574","title":"Can Machines Learn Morality? The Delphi Experiment","created":"2021-10-14","cited_by_count":141,"area":null},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2408.17003","title":"Safety Layers in Aligned Large Language Models: The Key to LLM Security","created":"2024-08-30","cited_by_count":134,"area":"alignment"},{"id":"2104.04670","title":"Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections","created":"2021-04-10","cited_by_count":128,"area":null},{"id":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128,"area":null},{"id":"2404.16698","title":"Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents","created":"2024-04-25","cited_by_count":125,"area":"wm"},{"id":"2311.05112","title":"A Survey of Large Language Models in Medicine: Progress, Application, and Challenge","created":"2023-11-09","cited_by_count":124,"area":null},{"id":"2305.18486","title":"A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets","created":"2023-05-29","cited_by_count":123,"area":null},{"id":"2502.16681","title":"Are Sparse Autoencoders Useful? A Case Study in Sparse Probing","created":"2025-02-23","cited_by_count":115,"area":"mechinterp"},{"id":"2205.12688","title":"ProsocialDialog: A Prosocial Backbone for Conversational Agents","created":"2022-05-25","cited_by_count":109,"area":"agents"},{"id":"2309.00779","title":"Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties","created":"2023-09-02","cited_by_count":97,"area":null},{"id":"2405.14577","title":"Representation Noising: A Defence Mechanism Against Harmful Finetuning","created":"2024-05-23","cited_by_count":96,"area":"safety"},{"id":"2204.03021","title":"The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems","created":"2022-04-06","cited_by_count":93,"area":null},{"id":"2210.01478","title":"When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment","created":"2022-10-04","cited_by_count":93,"area":null},{"id":"2406.05590","title":"NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security","created":"2024-06-08","cited_by_count":93,"area":null},{"id":"2402.16823","title":"Language Agents as Optimizable Graphs","created":"2024-02-26","cited_by_count":89,"area":"agents"},{"id":"2303.05453","title":"Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback","created":"2023-03-09","cited_by_count":87,"area":"alignment"},{"id":"2307.08678","title":"Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations","created":"2023-07-17","cited_by_count":85,"area":null},{"id":"2407.04069","title":"A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations","created":"2024-07-04","cited_by_count":85,"area":null},{"id":"2502.11211","title":"A Survey of LLM-based Agents in Medicine: How far are we from Baymax?","created":"2025-02-16","cited_by_count":85,"area":"agents"},{"id":"2308.04265","title":"FLIRT: Feedback Loop In-context Red Teaming","created":"2023-08-08","cited_by_count":83,"area":"safety"},{"id":"2508.17536","title":"Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?","created":"2025-08-24","cited_by_count":81,"area":"lr"},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"area":null},{"id":"2305.16960","title":"Training Socially Aligned Language Models on Simulated Social Interactions","created":"2023-05-26","cited_by_count":78,"area":"alignment"},{"id":"2402.18158","title":"Evaluating Quantized Large Language Models","created":"2024-02-28","cited_by_count":77,"area":null},{"id":"2404.05399","title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","created":"2024-04-08","cited_by_count":77,"area":"safety"},{"id":"2111.06719","title":"On Transferability of Prompt Tuning for Natural Language Processing","created":"2021-11-12","cited_by_count":75,"area":null},{"id":"2209.12106","title":"Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity","created":"2022-09-24","cited_by_count":74,"area":null},{"id":"2410.08827","title":"Do Unlearning Methods Remove Information from Language Model Weights?","created":"2024-10-11","cited_by_count":73,"area":"safety"},{"id":"2310.00280","title":"Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration","created":"2023-09-30","cited_by_count":70,"area":"lr"},{"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":"2405.11106","title":"LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions","created":"2024-05-17","cited_by_count":67,"area":"agents"},{"id":"2408.01122","title":"CFBench: A Comprehensive Constraints-Following Benchmark for LLMs","created":"2024-08-02","cited_by_count":67,"area":null},{"id":"2410.13284","title":"Learning to Route LLMs with Confidence Tokens","created":"2024-10-17","cited_by_count":67,"area":null},{"id":"2502.08640","title":"Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs","created":"2025-02-12","cited_by_count":67,"area":"agents"},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2402.01586","title":"TrustAgent: Towards Safe and Trustworthy LLM-based Agents","created":"2024-02-02","cited_by_count":64,"area":"agents"},{"id":"2303.11568","title":"Large AI Models in Health Informatics: Applications, Challenges, and the Future","created":"2023-03-21","cited_by_count":61,"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":"2206.05862","title":"X-Risk Analysis for AI Research","created":"2022-06-13","cited_by_count":60,"area":null},{"id":"2305.17008","title":"NormBank: A Knowledge Bank of Situational Social Norms","created":"2023-05-26","cited_by_count":60,"area":null},{"id":"2410.02683","title":"DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life","created":"2024-10-03","cited_by_count":59,"area":null},{"id":"2110.13136","title":"What Would Jiminy Cricket Do? Towards Agents That Behave Morally","created":"2021-10-25","cited_by_count":57,"area":null},{"id":"2305.00955","title":"Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation","created":"2023-05-01","cited_by_count":55,"area":"alignment"},{"id":"2407.15390","title":"ALLaM: Large Language Models for Arabic and English","created":"2024-07-22","cited_by_count":55,"area":null},{"id":"2310.07629","title":"The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values","created":"2023-10-11","cited_by_count":54,"area":"alignment"},{"id":"2301.05036","title":"Everyone's Voice Matters: Quantifying Annotation Disagreement Using Demographic Information","created":"2023-01-12","cited_by_count":52,"area":null},{"id":"2306.01857","title":"Knowledge of cultural moral norms in large language models","created":"2023-06-02","cited_by_count":51,"area":null},{"id":"2311.10766","title":"Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values","created":"2023-11-15","cited_by_count":50,"area":null},{"id":"2406.04428","title":"MoralBench: Moral Evaluation of LLMs","created":"2024-06-06","cited_by_count":50,"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":"2407.14507","title":"Internal Consistency and Self-Feedback in Large Language Models: A Survey","created":"2024-07-19","cited_by_count":50,"area":"lr"},{"id":"2206.08325","title":"Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models","created":"2022-06-16","cited_by_count":49,"area":null},{"id":"2401.06824","title":"Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective","created":"2024-01-12","cited_by_count":48,"area":"safety"},{"id":"2407.05975","title":"LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages","created":"2024-07-08","cited_by_count":48,"area":null},{"id":"2405.14125","title":"ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation","created":"2024-05-23","cited_by_count":47,"area":"agents"},{"id":"2311.04235","title":"Can LLMs Follow Simple Rules?","created":"2023-11-06","cited_by_count":46,"area":null},{"id":"2404.18460","title":"Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them in","created":"2024-04-29","cited_by_count":46,"area":"lr"},{"id":"2407.02273","title":"Language Model Alignment in Multilingual Trolley Problems","created":"2024-07-02","cited_by_count":46,"area":"alignment"},{"id":"2308.12014","title":"From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models","created":"2023-08-23","cited_by_count":45,"area":"alignment"},{"id":"2410.23252","title":"Evaluating Cultural and Social Awareness of LLM Web Agents","created":"2024-10-30","cited_by_count":45,"area":"agents"},{"id":"2310.19677","title":"MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks","created":"2023-10-30","cited_by_count":44,"area":"alignment"},{"id":"2502.08788","title":"Stop Overvaluing Multi-Agent Debate -- We Must Rethink Evaluation and Embrace Model Heterogeneity","created":"2025-02-12","cited_by_count":44,"area":"lr"}],"next_cursor":"100"}