{"total":168,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971,"area":"alignment"},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320,"area":null},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512,"area":null},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975,"area":null},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439,"area":"agents"},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395,"area":"agents"},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220,"area":null},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202,"area":null},{"id":"2211.14275","title":"Solving math word problems with process- and outcome-based feedback","created":"2022-11-25","cited_by_count":901,"area":"lr"},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808,"area":"agents"},{"id":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767,"area":null},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472,"area":"alignment"},{"id":"2312.00849","title":"RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback","created":"2023-12-01","cited_by_count":412,"area":"mllm"},{"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":"2306.13213","title":"Visual Adversarial Examples Jailbreak Aligned Large Language Models","created":"2023-06-22","cited_by_count":328,"area":"mllm"},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"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":"2308.03188","title":"Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies","created":"2023-08-06","cited_by_count":238,"area":"lr"},{"id":"2303.04226","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","created":"2023-03-07","cited_by_count":224,"area":null},{"id":"2306.09479","title":"Inverse Scaling: When Bigger Isn't Better","created":"2023-06-15","cited_by_count":207,"area":null},{"id":"2307.16039","title":"Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback","created":"2023-07-29","cited_by_count":190,"area":"alignment"},{"id":"2211.15006","title":"Fine-tuning language models to find agreement among humans with diverse preferences","created":"2022-11-28","cited_by_count":189,"area":"alignment"},{"id":"2106.10328","title":"Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets","created":"2021-06-18","cited_by_count":181,"area":null},{"id":"2309.09400","title":"CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages","created":"2023-09-17","cited_by_count":174,"area":null},{"id":"2401.06080","title":"Secrets of RLHF in Large Language Models Part II: Reward Modeling","created":"2024-01-11","cited_by_count":171,"area":"alignment"},{"id":"2309.17410","title":"Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks","created":"2023-09-29","cited_by_count":158,"area":null},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157,"area":null},{"id":"2307.09458","title":"Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla","created":"2023-07-18","cited_by_count":149,"area":null},{"id":"2401.03601","title":"InFoBench: Evaluating Instruction Following Ability in Large Language Models","created":"2024-01-07","cited_by_count":135,"area":null},{"id":"2306.11706","title":"RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation","created":"2023-06-20","cited_by_count":111,"area":"agents"},{"id":"2307.16513","title":"Deception Abilities Emerged in Large Language Models","created":"2023-07-31","cited_by_count":101,"area":null},{"id":"2311.02462","title":"Levels of AGI for Operationalizing Progress on the Path to AGI","created":"2023-11-04","cited_by_count":96,"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":"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":"2305.16960","title":"Training Socially Aligned Language Models on Simulated Social Interactions","created":"2023-05-26","cited_by_count":78,"area":"alignment"},{"id":"2312.07000","title":"Alignment for Honesty","created":"2023-12-12","cited_by_count":74,"area":"alignment"},{"id":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73,"area":null},{"id":"2209.00731","title":"In conversation with Artificial Intelligence: aligning language models with human values","created":"2022-09-01","cited_by_count":62,"area":"alignment"},{"id":"2311.06753","title":"AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs","created":"2023-11-12","cited_by_count":59,"area":"lr"},{"id":"2401.02038","title":"Understanding LLMs: A Comprehensive Overview from Training to Inference","created":"2024-01-04","cited_by_count":59,"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":"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":"2206.08325","title":"Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models","created":"2022-06-16","cited_by_count":49,"area":null},{"id":"2305.14965","title":"Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks","created":"2023-05-24","cited_by_count":49,"area":"safety"},{"id":"2307.02394","title":"Won't Get Fooled Again: Answering Questions with False Premises","created":"2023-07-05","cited_by_count":48,"area":null},{"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":"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":"2403.03744","title":"MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models","created":"2024-03-06","cited_by_count":44,"area":null},{"id":"2312.01350","title":"Honesty Is the Best Policy: Defining and Mitigating AI Deception","created":"2023-12-03","cited_by_count":40,"area":null},{"id":"2110.08300","title":"The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail","created":"2021-10-15","cited_by_count":38,"area":null},{"id":"2311.08993","title":"When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Tasks","created":"2023-11-15","cited_by_count":37,"area":null},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2402.10614","title":"Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements","created":"2024-02-16","cited_by_count":34,"area":null},{"id":"2402.13605","title":"KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge","created":"2024-02-21","cited_by_count":33,"area":"alignment"},{"id":"2405.17713","title":"AI Alignment with Changing and Influenceable Reward Functions","created":"2024-05-28","cited_by_count":33,"area":"alignment"},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2312.10029","title":"Challenges with unsupervised LLM knowledge discovery","created":"2023-12-15","cited_by_count":31,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2211.08714","title":"Reward Gaming in Conditional Text Generation","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2402.02056","title":"AnthroScore: A Computational Linguistic Measure of Anthropomorphism","created":"2024-02-03","cited_by_count":27,"area":null},{"id":"2312.06861","title":"Disentangling Perceptions of Offensiveness: Cultural and Moral Correlates","created":"2023-12-11","cited_by_count":26,"area":null},{"id":"2404.00934","title":"ChatGLM-RLHF: Practices of Aligning Large Language Models with Human Feedback","created":"2024-04-01","cited_by_count":25,"area":"alignment"},{"id":"2305.17701","title":"KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application","created":"2023-05-28","cited_by_count":24,"area":null},{"id":"2310.14303","title":"Language Model Unalignment: Parametric Red-Teaming to Expose Hidden Harms and Biases","created":"2023-10-22","cited_by_count":24,"area":"safety"},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2403.07708","title":"Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards","created":"2024-03-12","cited_by_count":23,"area":"alignment"},{"id":"2311.00710","title":"Interactive AI Alignment: Specification, Process, and Evaluation Alignment","created":"2023-10-23","cited_by_count":22,"area":null},{"id":"2203.16540","title":"Mind the gap: Challenges of deep learning approaches to Theory of Mind","created":"2022-03-30","cited_by_count":21,"area":null},{"id":"2403.04204","title":"On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models","created":"2024-03-07","cited_by_count":21,"area":"alignment"},{"id":"2204.10018","title":"Path-Specific Objectives for Safer Agent Incentives","created":"2022-04-21","cited_by_count":20,"area":null},{"id":"2402.08323","title":"Mapping the Ethics of Generative AI: A Comprehensive Scoping Review","created":"2024-02-13","cited_by_count":19,"area":null},{"id":"2502.07663","title":"Human Decision-making is Susceptible to AI-driven Manipulation","created":"2025-02-11","cited_by_count":19,"area":null},{"id":"2507.05619","title":"Detecting Proxy Gaming in RL and LLM Alignment via Evaluator Stress Tests","created":"2025-07-08","cited_by_count":19,"area":"alignment"},{"id":"2601.05214","title":"Internal Representations as Indicators of Hallucinations in Agent Tool Selection","created":"2026-01-08","cited_by_count":19,"area":"agents"},{"id":"2310.14587","title":"Large Search Model: Redefining Search Stack in the Era of LLMs","created":"2023-10-23","cited_by_count":18,"area":null},{"id":"2409.02795","title":"Towards a Unified View of Preference Learning for Large Language Models: A Survey","created":"2024-09-04","cited_by_count":17,"area":"alignment"},{"id":"2506.03320","title":"The Future of Continual Learning in the Era of Foundation Models: Three Key Directions","created":"2025-06-03","cited_by_count":17,"area":null},{"id":"2406.14928","title":"Autonomous Agents for Collaborative Task under Information Asymmetry","created":"2024-06-21","cited_by_count":16,"area":"agents"},{"id":"2410.02165","title":"A LLM-Powered Automatic Grading Framework with Human-Level Guidelines Optimization","created":"2024-10-03","cited_by_count":16,"area":null},{"id":"2411.02432","title":"Can LLMs make trade-offs involving stipulated pain and pleasure states?","created":"2024-11-01","cited_by_count":16,"area":null},{"id":"2303.02891","title":"Perspectives on the Social Impacts of Reinforcement Learning with Human Feedback","created":"2023-03-06","cited_by_count":15,"area":"alignment"},{"id":"2401.04620","title":"Agent Alignment in Evolving Social Norms","created":"2024-01-09","cited_by_count":15,"area":"agents"},{"id":"2412.17128","title":"Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models","created":"2024-12-22","cited_by_count":15,"area":null},{"id":"2306.00419","title":"Challenges and Remedies to Privacy and Security in AIGC: Exploring the Potential of Privacy Computing, Blockchain, and Beyond","created":"2023-06-01","cited_by_count":14,"area":null},{"id":"2410.05328","title":"Reward Learning From Preference With Ties","created":"2024-10-05","cited_by_count":14,"area":"alignment"},{"id":"2305.17696","title":"SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine Collaboration","created":"2023-05-28","cited_by_count":13,"area":null},{"id":"2312.11819","title":"An Adaptive Placement and Parallelism Framework for Accelerating RLHF Training","created":"2023-12-19","cited_by_count":13,"area":"alignment"},{"id":"2405.08597","title":"Risks and Opportunities of Open-Source Generative AI","created":"2024-05-14","cited_by_count":13,"area":null},{"id":"2505.17712","title":"Understanding How Value Neurons Shape the Generation of Specified Values in LLMs","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2303.13360","title":"Towards the Scalable Evaluation of Cooperativeness in Language Models","created":"2023-03-16","cited_by_count":12,"area":null},{"id":"2310.02842","title":"Sweeping Heterogeneity with Smart MoPs: Mixture of Prompts for LLM Task Adaptation","created":"2023-10-04","cited_by_count":12,"area":null},{"id":"2405.13516","title":"LIRE: listwise reward enhancement for preference alignment","created":"2024-05-22","cited_by_count":11,"area":"alignment"},{"id":"2407.09221","title":"Evaluating AI Evaluation: Perils and Prospects","created":"2024-07-12","cited_by_count":11,"area":null},{"id":"2109.14728","title":"Collaborative Storytelling with Human Actors and AI Narrators","created":"2021-09-29","cited_by_count":10,"area":null},{"id":"2406.07295","title":"Multi-objective Reinforcement learning from AI Feedback","created":"2024-06-11","cited_by_count":10,"area":"alignment"},{"id":"2407.00942","title":"ProductAgent: Benchmarking Conversational Product Search Agent with Asking Clarification Questions","created":"2024-07-01","cited_by_count":10,"area":"agents"},{"id":"2507.20333","title":"The Blessing and Curse of Dimensionality in Safety Alignment","created":"2025-07-27","cited_by_count":10,"area":"alignment"}],"next_cursor":"100"}