{"total":290,"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":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568,"area":"wm"},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2310.08560","title":"MemGPT: Towards LLMs as Operating Systems","created":"2023-10-12","cited_by_count":1389,"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":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055,"area":"alignment"},{"id":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045,"area":null},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026,"area":"safety"},{"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":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886,"area":"lr"},{"id":"2310.04451","title":"AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models","created":"2023-10-03","cited_by_count":785,"area":"alignment"},{"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":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751,"area":null},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686,"area":"lr"},{"id":"2404.13076","title":"LLM Evaluators Recognize and Favor Their Own Generations","created":"2024-04-15","cited_by_count":686,"area":"alignment"},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656,"area":"alignment"},{"id":"2401.18059","title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","created":"2024-01-31","cited_by_count":532,"area":"rag"},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531,"area":"agents"},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2308.08998","title":"Reinforced Self-Training (ReST) for Language Modeling","created":"2023-08-17","cited_by_count":500,"area":"alignment"},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499,"area":"alignment"},{"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":"2304.05302","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","created":"2023-04-11","cited_by_count":463,"area":"alignment"},{"id":"2309.17400","title":"Directly Fine-Tuning Diffusion Models on Differentiable Rewards","created":"2023-09-29","cited_by_count":448,"area":"diffusion"},{"id":"2301.13848","title":"Benchmarking Large Language Models for News Summarization","created":"2023-01-31","cited_by_count":445,"area":null},{"id":"2302.12192","title":"Aligning Text-to-Image Models using Human Feedback","created":"2023-02-23","cited_by_count":422,"area":"alignment"},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403,"area":"lr"},{"id":"2306.01693","title":"Fine-Grained Human Feedback Gives Better Rewards for Language Model Training","created":"2023-06-02","cited_by_count":401,"area":"alignment"},{"id":"2206.05802","title":"Self-critiquing models for assisting human evaluators","created":"2022-06-12","cited_by_count":380,"area":null},{"id":"2312.11456","title":"Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint","created":"2023-12-18","cited_by_count":350,"area":"alignment"},{"id":"2512.13564","title":"Memory in the Age of AI Agents","created":"2025-12-15","cited_by_count":303,"area":"agents"},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2310.11564","title":"Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging","created":"2023-10-17","cited_by_count":280,"area":"alignment"},{"id":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267,"area":"lr"},{"id":"2312.14925","title":"A Survey of Reinforcement Learning from Human Feedback","created":"2023-12-22","cited_by_count":264,"area":"alignment"},{"id":"2311.08268","title":"A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily","created":"2023-11-14","cited_by_count":259,"area":"safety"},{"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":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247,"area":"alignment"},{"id":"2210.01241","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","created":"2022-10-03","cited_by_count":246,"area":null},{"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,"area":"alignment"},{"id":"2310.02743","title":"Reward Model Ensembles Help Mitigate Overoptimization","created":"2023-10-04","cited_by_count":231,"area":"alignment"},{"id":"2211.03540","title":"Measuring Progress on Scalable Oversight for Large Language Models","created":"2022-11-04","cited_by_count":225,"area":null},{"id":"2311.04939","title":"LooGLE: Can Long-Context Language Models Understand Long Contexts?","created":"2023-11-08","cited_by_count":202,"area":null},{"id":"2209.14958","title":"Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionals","created":"2022-09-29","cited_by_count":191,"area":null},{"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":"2309.06256","title":"Mitigating the Alignment Tax of RLHF","created":"2023-09-12","cited_by_count":183,"area":"alignment"},{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177,"area":null},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2402.09727","title":"A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts","created":"2024-02-15","cited_by_count":146,"area":"agents"},{"id":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146,"area":null},{"id":"2310.00785","title":"BooookScore: A systematic exploration of book-length summarization in the era of LLMs","created":"2023-10-01","cited_by_count":137,"area":null},{"id":"2310.05029","title":"Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading","created":"2023-10-08","cited_by_count":133,"area":null},{"id":"2305.10626","title":"Language Models Meet World Models: Embodied Experiences Enhance Language Models","created":"2023-05-18","cited_by_count":124,"area":"wm"},{"id":"2402.10571","title":"Direct Preference Optimization with an Offset","created":"2024-02-16","cited_by_count":122,"area":"alignment"},{"id":"2406.10252","title":"AutoSurvey: Large Language Models Can Automatically Write Surveys","created":"2024-06-10","cited_by_count":119,"area":null},{"id":"2401.02906","title":"MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance","created":"2024-01-05","cited_by_count":117,"area":"mllm"},{"id":"2402.03293","title":"Flora: Low-Rank Adapters Are Secretly Gradient Compressors","created":"2024-02-05","cited_by_count":108,"area":null},{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106,"area":null},{"id":"2401.04259","title":"MARG: Multi-Agent Review Generation for Scientific Papers","created":"2024-01-08","cited_by_count":104,"area":"agents"},{"id":"2512.24601","title":"Recursive Language Models","created":"2025-12-31","cited_by_count":104,"area":"lr"},{"id":"2403.02901","title":"A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods","created":"2024-03-05","cited_by_count":102,"area":null},{"id":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100,"area":"lr"},{"id":"2304.13343","title":"SCM: Enhancing Large Language Model with Self-Controlled Memory Framework","created":"2023-04-26","cited_by_count":98,"area":null},{"id":"2203.10050","title":"SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning","created":"2022-03-18","cited_by_count":97,"area":"alignment"},{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96,"area":"alignment"},{"id":"2302.11520","title":"Guiding Large Language Models via Directional Stimulus Prompting","created":"2023-02-22","cited_by_count":95,"area":null},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2311.18232","title":"LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models","created":"2023-11-30","cited_by_count":88,"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":"2407.13692","title":"Prover-Verifier Games improve legibility of LLM outputs","created":"2024-07-18","cited_by_count":85,"area":null},{"id":"2410.02832","title":"FlipAttack: Jailbreak LLMs via Flipping","created":"2024-10-02","cited_by_count":80,"area":"safety"},{"id":"2303.00957","title":"Preference Transformer: Modeling Human Preferences using Transformers for RL","created":"2023-03-02","cited_by_count":79,"area":null},{"id":"2402.00782","title":"Dense Reward for Free in Reinforcement Learning from Human Feedback","created":"2024-02-01","cited_by_count":78,"area":"alignment"},{"id":"2403.08730","title":"Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization","created":"2024-03-13","cited_by_count":75,"area":"mllm"},{"id":"2306.00186","title":"Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2407.01599","title":"JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models","created":"2024-06-26","cited_by_count":70,"area":"mllm"},{"id":"2305.15363","title":"Inverse Preference Learning: Preference-based RL without a Reward Function","created":"2023-05-24","cited_by_count":68,"area":"alignment"},{"id":"2110.10150","title":"Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents","created":"2021-10-16","cited_by_count":65,"area":null},{"id":"2406.10794","title":"Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis","created":"2024-06-16","cited_by_count":64,"area":"safety"},{"id":"2504.17704","title":"Safety in Large Reasoning Models: A Survey","created":"2025-04-24","cited_by_count":64,"area":"lr"},{"id":"2302.05206","title":"The Wisdom of Hindsight Makes Language Models Better Instruction Followers","created":"2023-02-10","cited_by_count":62,"area":"alignment"},{"id":"2205.12401","title":"Reward Uncertainty for Exploration in Preference-based Reinforcement Learning","created":"2022-05-24","cited_by_count":61,"area":"alignment"},{"id":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58,"area":"alignment"},{"id":"2401.16335","title":"Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF","created":"2024-01-29","cited_by_count":57,"area":"alignment"},{"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":"2305.14816","title":"Provable Offline Preference-Based Reinforcement Learning","created":"2023-05-24","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":"2402.07314","title":"Online Iterative Reinforcement Learning from Human Feedback with General Preference Model","created":"2024-02-11","cited_by_count":52,"area":"alignment"},{"id":"2406.11289","title":"A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models","created":"2024-06-17","cited_by_count":52,"area":null},{"id":"2205.11465","title":"SQuALITY: Building a Long-Document Summarization Dataset the Hard Way","created":"2022-05-23","cited_by_count":50,"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":"2404.03602","title":"Evaluating LLMs at Detecting Errors in LLM Responses","created":"2024-04-04","cited_by_count":50,"area":null},{"id":"2306.11816","title":"Learning to Generate Better Than Your LLM","created":"2023-06-20","cited_by_count":49,"area":null},{"id":"2405.06639","title":"Value Augmented Sampling for Language Model Alignment and Personalization","created":"2024-05-10","cited_by_count":49,"area":"alignment"},{"id":"2212.10938","title":"Critic-Guided Decoding for Controlled Text Generation","created":"2022-12-21","cited_by_count":45,"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":"2406.01940","title":"Process-Driven Autoformalization in Lean 4","created":"2024-06-04","cited_by_count":45,"area":"lr"},{"id":"2211.15914","title":"Prompted Opinion Summarization with GPT-3.5","created":"2022-11-29","cited_by_count":44,"area":null},{"id":"2510.05024","title":"Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment","created":"2025-10-06","cited_by_count":43,"area":"alignment"}],"next_cursor":"100"}