{"total":44,"rows":[{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075,"area":"lr"},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686,"area":"lr"},{"id":"2501.18101","title":"Diverse Preference Optimization","created":"2025-01-30","cited_by_count":52,"area":"lr"},{"id":"2504.12522","title":"Evaluating the Diversity and Quality of LLM Generated Content","created":"2025-04-16","cited_by_count":51,"area":"lr"},{"id":"2308.10855","title":"LatEval: An Interactive LLMs Evaluation Benchmark with Incomplete Information from Lateral Thinking Puzzles","created":"2023-08-21","cited_by_count":41,"area":"lr"},{"id":"2508.01491","title":"The Homogenizing Effect of Large Language Models on Human Expression and Thought","created":"2025-08-02","cited_by_count":35,"area":"lr"},{"id":"2305.17878","title":"Ask an Expert: Leveraging Language Models to Improve Strategic Reasoning in Goal-Oriented Dialogue Models","created":"2023-05-29","cited_by_count":31,"area":"lr"},{"id":"2307.02768","title":"Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts","created":"2023-07-06","cited_by_count":31,"area":"lr"},{"id":"2407.05013","title":"Progress or Regress? Self-Improvement Reversal in Post-training","created":"2024-07-06","cited_by_count":23,"area":"lr"},{"id":"2604.06268","title":"RAGEN-2: Reasoning Collapse in Agentic RL","created":"2026-04-07","cited_by_count":20,"area":"lr"},{"id":"2203.07285","title":"Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Experts","created":"2022-03-14","cited_by_count":19,"area":"lr"},{"id":"2404.16807","title":"Improving Diversity of Commonsense Generation by Large Language Models via In-Context Learning","created":"2024-04-25","cited_by_count":19,"area":"lr"},{"id":"2509.26578","title":"Linking Process to Outcome: Conditional Reward Modeling for LLM Reasoning","created":"2025-09-30","cited_by_count":14,"area":"lr"},{"id":"2410.23703","title":"OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models","created":"2024-10-31","cited_by_count":12,"area":"lr"},{"id":"2509.23232","title":"SPEC-RL: Accelerating On-Policy Reinforcement Learning with Speculative Rollouts","created":"2025-09-27","cited_by_count":12,"area":"lr"},{"id":"2311.07445","title":"Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue","created":"2023-11-13","cited_by_count":11,"area":"lr"},{"id":"2408.11599","title":"Cause-Aware Empathetic Response Generation via Chain-of-Thought Fine-Tuning","created":"2024-08-21","cited_by_count":11,"area":"lr"},{"id":"2508.04117","title":"Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks","created":"2025-08-06","cited_by_count":11,"area":"lr"},{"id":"2506.15629","title":"Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability","created":"2025-06-18","cited_by_count":10,"area":"lr"},{"id":"2507.20187","title":"Diversity-Enhanced Reasoning for Subjective Questions","created":"2025-07-27","cited_by_count":9,"area":"lr"},{"id":"2509.17570","title":"Asking a Language Model for Diverse Responses","created":"2025-09-22","cited_by_count":9,"area":"lr"},{"id":"2401.09082","title":"Should agentic conversational AI change how we think about ethics? Characterising an interactional ethics centred on respect","created":"2024-01-17","cited_by_count":8,"area":"lr"},{"id":"2502.09447","title":"Pixel-Level Reasoning Segmentation via Multi-turn Conversations","created":"2025-02-13","cited_by_count":7,"area":"lr"},{"id":"2508.03140","title":"RCP-Merging: Merging Long Chain-of-Thought Models with Domain-Specific Models by Considering Reasoning Capability as Prior","created":"2025-08-05","cited_by_count":5,"area":"lr"},{"id":"2508.10164","title":"Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization","created":"2025-08-13","cited_by_count":3,"area":"lr"},{"id":"2508.19200","title":"The Ramon Llull's Thinking Machine for Automated Ideation","created":"2025-08-26","cited_by_count":3,"area":"lr"},{"id":"2601.22629","title":"Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Models","created":"2026-01-30","cited_by_count":3,"area":"lr"},{"id":"2609.28145","title":"RL Starts before RL: On Policy Distillation for Better Reinforcement Learning","created":"2026-09-23","cited_by_count":3,"area":"lr"},{"id":"2405.10251","title":"A Systematic Evaluation of Large Language Models for Natural Language Generation Tasks","created":"2024-05-16","cited_by_count":2,"area":"lr"},{"id":"2510.13499","title":"ConsintBench: Evaluating Language Models on Real-World Consumer Intent Understanding","created":"2025-10-15","cited_by_count":2,"area":"lr"},{"id":"2502.13207","title":"Thinking Outside the (Gray) Box: A Context-Based Score for Assessing Value and Originality in Neural Text Generation","created":"2025-02-18","cited_by_count":1,"area":"lr"},{"id":"2601.17842","title":"EFT-CoT: A Multi-Agent Chain-of-Thought Framework for Emotion-Focused Therapy","created":"2026-01-25","cited_by_count":1,"area":"lr"},{"id":"2604.20500","title":"Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees","created":"2026-04-22","cited_by_count":1,"area":"lr"},{"id":"2506.10086","title":"Chat-of-Thought: Collaborative Multi-Agent System for Generating Domain Specific Information","created":"2025-06-11","cited_by_count":0,"area":"lr"},{"id":"2508.05234","title":"Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation","created":"2025-08-07","cited_by_count":0,"area":"lr"},{"id":"2601.22546","title":"Towards the Holographic Characteristic of LLMs for Efficient Short-text Generation","created":"2026-01-30","cited_by_count":0,"area":"lr"},{"id":"2603.21329","title":"COINBench: Moving Beyond Individual Perspectives to Collective Intent Understanding","created":"2026-03-22","cited_by_count":0,"area":"lr"},{"id":"2604.19464","title":"LePREC: Reasoning as Classification over Structured Factors for Assessing Relevance of Legal Issues","created":"2026-04-21","cited_by_count":0,"area":"lr"},{"id":"2605.09853","title":"Exploration-Driven Optimization for Test-Time Large Language Model Reasoning","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2606.12902","title":"PRISM: Prosody-Integrated Multi-Agent Reasoning Framework for Empathetic Spoken Dialogue","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2609.01188","title":"PersuaRL: Reinforcement Learning-Driven Multi-Expert Selection for Persuasive Dialogue Generation in Insurance","created":"2026-09-01","cited_by_count":0,"area":"lr"},{"id":"2609.31571","title":"Strategically Diverse Sampling for Self-Training","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.36535","title":"When Updating Stops Being Learning: Rethinking LLM Self-Evolution via learnable information gain","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.16755","title":"The Multilingual Artificial Hivemind: Do All LLMs Think Alike in Every Language?","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}