{"list":"other","total":54,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2305.14992","title":"Reasoning with Language Model is Planning with World Model","created":"2023-05-24","cited_by_count":861},{"id":"1910.00177","title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","created":"2019-10-01","cited_by_count":782},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672},{"id":"2403.09629","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","created":"2024-03-14","cited_by_count":301},{"id":"2402.06457","title":"V-STaR: Training Verifiers for Self-Taught Reasoners","created":"2024-02-09","cited_by_count":217},{"id":"1909.05378","title":"CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases","created":"2019-09-11","cited_by_count":185},{"id":"1503.02834","title":"Doubly Robust Policy Evaluation and Optimization","created":"2015-03-10","cited_by_count":158},{"id":"2206.11871","title":"Offline RL for Natural Language Generation with Implicit Language Q Learning","created":"2022-06-05","cited_by_count":138},{"id":"2305.14536","title":"MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems","created":"2023-05-23","cited_by_count":131},{"id":"2304.14399","title":"We're Afraid Language Models Aren't Modeling Ambiguity","created":"2023-04-27","cited_by_count":126},{"id":"1902.03736","title":"A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm","created":"2019-02-11","cited_by_count":106},{"id":"2403.19154","title":"STaR-GATE: Teaching Language Models to Ask Clarifying Questions","created":"2024-03-28","cited_by_count":104},{"id":"2010.05848","title":"Human-centric Dialog Training via Offline Reinforcement Learning","created":"2020-10-12","cited_by_count":93},{"id":"2202.13330","title":"DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following","created":"2022-02-27","cited_by_count":63},{"id":"2406.12639","title":"Ask-before-Plan: Proactive Language Agents for Real-World Planning","created":"2024-06-18","cited_by_count":60},{"id":"2406.00222","title":"Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training","created":"2024-05-31","cited_by_count":57},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52},{"id":"2409.16490","title":"Exploring Knowledge Tracing in Tutor-Student Dialogues using LLMs","created":"2024-09-24","cited_by_count":46},{"id":"2503.03710","title":"Improving LLM Safety Alignment with Dual-Objective Optimization","created":"2025-03-05","cited_by_count":43},{"id":"2503.06424","title":"Training LLM-based Tutors to Improve Student Learning Outcomes in Dialogues","created":"2025-03-09","cited_by_count":43},{"id":"2311.05584","title":"Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations","created":"2023-11-09","cited_by_count":38},{"id":"2412.06771","title":"Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty","created":"2024-12-09","cited_by_count":25},{"id":"1712.02838","title":"End-to-End Offline Goal-Oriented Dialog Policy Learning via Policy Gradient","created":"2017-12-07","cited_by_count":23},{"id":"2206.09674","title":"EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL","created":"2022-06-20","cited_by_count":23},{"id":"2502.04485","title":"Active Task Disambiguation with LLMs","created":"2025-02-06","cited_by_count":23},{"id":"2405.15784","title":"CLARINET: Augmenting Language Models to Ask Clarification Questions for Retrieval","created":"2024-04-28","cited_by_count":20},{"id":"1901.04723","title":"Imitation-Regularized Offline Learning","created":"2019-01-15","cited_by_count":17},{"id":"2305.14718","title":"Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models","created":"2023-05-24","cited_by_count":17},{"id":"2502.02797","title":"Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting","created":"2025-02-05","cited_by_count":16},{"id":"2503.01940","title":"AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification","created":"2025-03-03","cited_by_count":13},{"id":"2409.14195","title":"The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends","created":"2024-09-21","cited_by_count":11},{"id":"2411.05193","title":"Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning","created":"2024-11-07","cited_by_count":10},{"id":"2503.07377","title":"Process-Supervised LLM Recommenders via Flow-guided Tuning","created":"2025-03-10","cited_by_count":10},{"id":"2212.11431","title":"Local Policy Improvement for Recommender Systems","created":"2022-12-22","cited_by_count":9},{"id":"2201.00235","title":"Simulating and Modeling the Risk of Conversational Search","created":"2022-01-01","cited_by_count":6},{"id":"2403.17582","title":"Towards a Zero-Data, Controllable, Adaptive Dialog System","created":"2024-03-26","cited_by_count":4},{"id":"2410.23912","title":"RL-STaR: Theoretical Analysis of Reinforcement Learning Frameworks for Self-Taught Reasoner","created":"2024-10-31","cited_by_count":4},{"id":"2502.19409","title":"ImageChain: Advancing Sequential Image-to-Text Reasoning in Multimodal Large Language Models","created":"2025-02-26","cited_by_count":4},{"id":"2503.00179","title":"Zero-Shot and Efficient Clarification Need Prediction in Conversational Search","created":"2025-02-28","cited_by_count":4},{"id":"2403.02754","title":"Learning to Ask Critical Questions for Assisting Product Search","created":"2024-03-05","cited_by_count":3},{"id":"2412.15995","title":"Data-Centric Improvements for Enhancing Multi-Modal Understanding in Spoken Conversation Modeling","created":"2024-12-20","cited_by_count":3},{"id":"2401.05822","title":"Towards Goal-Oriented Agents for Evolving Problems Observed via Conversation","created":"2024-01-11","cited_by_count":1}],"next_cursor":null}