{"total":365,"rows":[{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065,"area":"lr"},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588,"area":"alignment"},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150,"area":"alignment"},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392,"area":null},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135,"area":null},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748,"area":"alignment"},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609,"area":null},{"id":"2404.05961","title":"LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders","created":"2024-04-09","cited_by_count":404,"area":null},{"id":"2305.10425","title":"SLiC-HF: Sequence Likelihood Calibration with Human Feedback","created":"2023-05-17","cited_by_count":401,"area":"alignment"},{"id":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384,"area":"lr"},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328,"area":"alignment"},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273,"area":null},{"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":"2103.12693","title":"QuestEval: Summarization Asks for Fact-based Evaluation","created":"2021-03-23","cited_by_count":244,"area":null},{"id":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237,"area":"safety"},{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228,"area":"agents"},{"id":"2105.08209","title":"BookSum: A Collection of Datasets for Long-form Narrative Summarization","created":"2021-05-18","cited_by_count":184,"area":null},{"id":"2105.06762","title":"DialogSum: A Real-Life Scenario Dialogue Summarization Dataset","created":"2021-05-14","cited_by_count":183,"area":null},{"id":"2203.16804","title":"BRIO: Bringing Order to Abstractive Summarization","created":"2022-03-31","cited_by_count":161,"area":null},{"id":"2403.06963","title":"The pitfalls of next-token prediction","created":"2024-03-11","cited_by_count":160,"area":null},{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155,"area":null},{"id":"2206.11871","title":"Offline RL for Natural Language Generation with Implicit Language Q Learning","created":"2022-06-05","cited_by_count":138,"area":"offlinerl"},{"id":"2205.11275","title":"RL with KL penalties is better viewed as Bayesian inference","created":"2022-05-23","cited_by_count":135,"area":null},{"id":"2106.01890","title":"SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization","created":"2021-06-03","cited_by_count":132,"area":null},{"id":"2409.12822","title":"Language Models Learn to Mislead Humans via RLHF","created":"2024-09-19","cited_by_count":124,"area":"alignment"},{"id":"2201.05273","title":"Pretrained Language Models for Text Generation: A Survey","created":"2022-01-14","cited_by_count":122,"area":null},{"id":"2210.00045","title":"Calibrating Sequence likelihood Improves Conditional Language Generation","created":"2022-09-30","cited_by_count":121,"area":null},{"id":"2108.03353","title":"Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning","created":"2021-08-07","cited_by_count":120,"area":null},{"id":"2302.08215","title":"Aligning Language Models with Preferences through f-divergence Minimization","created":"2023-02-16","cited_by_count":120,"area":"alignment"},{"id":"2307.15190","title":"f-Divergence Minimization for Sequence-Level Knowledge Distillation","created":"2023-07-27","cited_by_count":114,"area":"distill"},{"id":"2212.07525","title":"Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language","created":"2022-12-14","cited_by_count":110,"area":null},{"id":"2302.11520","title":"Guiding Large Language Models via Directional Stimulus Prompting","created":"2023-02-22","cited_by_count":95,"area":null},{"id":"2206.02369","title":"Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation","created":"2022-06-06","cited_by_count":94,"area":null},{"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":"2206.00761","title":"On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting","created":"2022-06-01","cited_by_count":82,"area":null},{"id":"2305.14239","title":"On Learning to Summarize with Large Language Models as References","created":"2023-05-23","cited_by_count":80,"area":null},{"id":"2104.07091","title":"SummScreen: A Dataset for Abstractive Screenplay Summarization","created":"2021-04-14","cited_by_count":79,"area":null},{"id":"2107.03451","title":"Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling","created":"2021-07-07","cited_by_count":78,"area":null},{"id":"2207.00939","title":"An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics","created":"2022-07-03","cited_by_count":74,"area":null},{"id":"2308.16898","title":"Transformers as Support Vector Machines","created":"2023-08-31","cited_by_count":74,"area":null},{"id":"2101.11796","title":"DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents","created":"2021-01-28","cited_by_count":70,"area":null},{"id":"2112.08558","title":"CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning","created":"2021-12-16","cited_by_count":68,"area":null},{"id":"2303.07284","title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","created":"2023-03-13","cited_by_count":65,"area":null},{"id":"2102.00176","title":"Can We Automate Scientific Reviewing?","created":"2021-01-30","cited_by_count":63,"area":null},{"id":"2307.15703","title":"Uncertainty in Natural Language Generation: From Theory to Applications","created":"2023-07-28","cited_by_count":61,"area":null},{"id":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59,"area":null},{"id":"2306.13596","title":"Max-Margin Token Selection in Attention Mechanism","created":"2023-06-23","cited_by_count":58,"area":null},{"id":"1805.10627","title":"Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning","created":"2018-05-27","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":"2402.08265","title":"A Dense Reward View on Aligning Text-to-Image Diffusion with Preference","created":"2024-02-13","cited_by_count":55,"area":"diffusion"},{"id":"2405.18540","title":"Learning diverse attacks on large language models for robust red-teaming and safety tuning","created":"2024-05-28","cited_by_count":54,"area":"safety"},{"id":"2305.14106","title":"Better Zero-Shot Reasoning with Self-Adaptive Prompting","created":"2023-05-23","cited_by_count":52,"area":"lr"},{"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":"2103.11332","title":"AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization","created":"2021-03-21","cited_by_count":51,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2204.14146","title":"Training Language Models with Language Feedback","created":"2022-04-29","cited_by_count":49,"area":"alignment"},{"id":"2306.02231","title":"Fine-Tuning Language Models with Advantage-Induced Policy Alignment","created":"2023-06-04","cited_by_count":48,"area":"alignment"},{"id":"2109.03171","title":"Aspect-Controllable Opinion Summarization","created":"2021-09-07","cited_by_count":47,"area":null},{"id":"2212.10938","title":"Critic-Guided Decoding for Controlled Text Generation","created":"2022-12-21","cited_by_count":45,"area":null},{"id":"2304.04052","title":"Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder","created":"2023-04-08","cited_by_count":44,"area":null},{"id":"2103.16057","title":"Grounding Open-Domain Instructions to Automate Web Support Tasks","created":"2021-03-30","cited_by_count":43,"area":null},{"id":"2109.11503","title":"Finding a Balanced Degree of Automation for Summary Evaluation","created":"2021-09-23","cited_by_count":43,"area":null},{"id":"2210.03078","title":"Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering","created":"2022-10-06","cited_by_count":43,"area":null},{"id":"2308.08758","title":"Discrete Prompt Compression with Reinforcement Learning","created":"2023-08-17","cited_by_count":42,"area":"inference"},{"id":"2310.09144","title":"Goodhart's Law in Reinforcement Learning","created":"2023-10-13","cited_by_count":41,"area":null},{"id":"2109.02903","title":"IndicBART: A Pre-trained Model for Indic Natural Language Generation","created":"2021-09-07","cited_by_count":39,"area":null},{"id":"2311.05584","title":"Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations","created":"2023-11-09","cited_by_count":38,"area":null},{"id":"2106.07704","title":"Efficient (Soft) Q-Learning for Text Generation with Limited Good Data","created":"2021-06-14","cited_by_count":37,"area":null},{"id":"2203.07472","title":"Uncertainty Estimation for Language Reward Models","created":"2022-03-14","cited_by_count":37,"area":"alignment"},{"id":"2104.08400","title":"Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs","created":"2021-04-16","cited_by_count":36,"area":null},{"id":"2109.13070","title":"Controllable Neural Dialogue Summarization with Personal Named Entity Planning","created":"2021-09-27","cited_by_count":36,"area":null},{"id":"2402.12366","title":"A Critical Evaluation of AI Feedback for Aligning Large Language Models","created":"2024-02-19","cited_by_count":36,"area":"alignment"},{"id":"2102.02723","title":"Data-to-text Generation with Macro Planning","created":"2021-02-04","cited_by_count":34,"area":null},{"id":"2106.00130","title":"Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents","created":"2021-05-31","cited_by_count":33,"area":null},{"id":"2305.15065","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2104.07545","title":"Hierarchical Learning for Generation with Long Source Sequences","created":"2021-04-15","cited_by_count":32,"area":null},{"id":"2109.02401","title":"Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization","created":"2021-09-06","cited_by_count":32,"area":null},{"id":"2212.04972","title":"MOPRD: A multidisciplinary open peer review dataset","created":"2022-12-09","cited_by_count":32,"area":null},{"id":"2109.03481","title":"Sequence Level Contrastive Learning for Text Summarization","created":"2021-09-08","cited_by_count":31,"area":null},{"id":"2306.00398","title":"Preference-grounded Token-level Guidance for Language Model Fine-tuning","created":"2023-06-01","cited_by_count":31,"area":"alignment"},{"id":"2403.18447","title":"Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction","created":"2024-03-27","cited_by_count":31,"area":null},{"id":"2109.04953","title":"Does Pretraining for Summarization Require Knowledge Transfer?","created":"2021-09-10","cited_by_count":30,"area":null},{"id":"2305.02468","title":"Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System","created":"2023-05-04","cited_by_count":30,"area":null},{"id":"2204.13154","title":"Attention Mechanism in Neural Networks: Where it Comes and Where it Goes","created":"2022-04-27","cited_by_count":29,"area":null},{"id":"2103.13597","title":"Mask Attention Networks: Rethinking and Strengthen Transformer","created":"2021-03-25","cited_by_count":28,"area":null},{"id":"2105.05361","title":"The Summary Loop: Learning to Write Abstractive Summaries Without Examples","created":"2021-05-11","cited_by_count":27,"area":null},{"id":"2105.14064","title":"Controllable Abstractive Dialogue Summarization with Sketch Supervision","created":"2021-05-28","cited_by_count":27,"area":null},{"id":"2310.20703","title":"Vanishing Gradients in Reinforcement Finetuning of Language Models","created":"2023-10-31","cited_by_count":27,"area":null},{"id":"2312.04782","title":"Make Them Spill the Beans! Coercive Knowledge Extraction from (Production) LLMs","created":"2023-12-08","cited_by_count":27,"area":null},{"id":"2407.18698","title":"Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation","created":"2024-07-26","cited_by_count":27,"area":null},{"id":"2203.09629","title":"HiStruct+: Improving Extractive Text Summarization with Hierarchical Structure Information","created":"2022-03-17","cited_by_count":26,"area":null},{"id":"2104.07210","title":"RefSum: Refactoring Neural Summarization","created":"2021-04-15","cited_by_count":25,"area":null},{"id":"2109.04325","title":"Learning Opinion Summarizers by Selecting Informative Reviews","created":"2021-09-09","cited_by_count":25,"area":null},{"id":"2403.08032","title":"LG-Traj: LLM Guided Pedestrian Trajectory Prediction","created":"2024-03-12","cited_by_count":25,"area":null},{"id":"2305.14711","title":"Gender Biases in Automatic Evaluation Metrics for Image Captioning","created":"2023-05-24","cited_by_count":24,"area":null},{"id":"2309.01038","title":"Neurosymbolic Reinforcement Learning and Planning: A Survey","created":"2023-09-02","cited_by_count":24,"area":null},{"id":"2106.10158","title":"Learning to Complete Code with Sketches","created":"2021-06-18","cited_by_count":23,"area":null},{"id":"2109.04994","title":"Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization","created":"2021-09-10","cited_by_count":23,"area":null},{"id":"2107.00176","title":"Reinforcement Learning for Abstractive Question Summarization with Question-aware Semantic Rewards","created":"2021-07-01","cited_by_count":22,"area":null}],"next_cursor":"100"}