{"total":36,"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":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403,"area":"lr"},{"id":"2402.01306","title":"KTO: Model Alignment as Prospect Theoretic Optimization","created":"2024-02-02","cited_by_count":264,"area":"lr"},{"id":"2506.01347","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","created":"2025-06-02","cited_by_count":162,"area":"lr"},{"id":"2306.03872","title":"Deductive Verification of Chain-of-Thought Reasoning","created":"2023-06-06","cited_by_count":124,"area":"lr"},{"id":"2505.23585","title":"On-Policy RL with Optimal Reward Baseline","created":"2025-05-29","cited_by_count":34,"area":"lr"},{"id":"2301.00355","title":"Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits","created":"2023-01-01","cited_by_count":27,"area":"lr"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2602.20710","title":"Counterfactual Simulation Training for Chain-of-Thought Faithfulness","created":"2026-02-24","cited_by_count":17,"area":"lr"},{"id":"2312.14591","title":"Reasons to Reject? Aligning Language Models with Judgments","created":"2023-12-22","cited_by_count":15,"area":"lr"},{"id":"2410.17050","title":"UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs","created":"2024-10-22","cited_by_count":15,"area":"lr"},{"id":"2510.02172","title":"RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization","created":"2025-10-02","cited_by_count":15,"area":"lr"},{"id":"2304.01665","title":"Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks","created":"2023-04-04","cited_by_count":12,"area":"lr"},{"id":"2303.03628","title":"CoTEVer: Chain of Thought Prompting Annotation Toolkit for Explanation Verification","created":"2023-03-07","cited_by_count":11,"area":"lr"},{"id":"2402.03469","title":"Rethinking the Role of Proxy Rewards in Language Model Alignment","created":"2024-02-02","cited_by_count":7,"area":"lr"},{"id":"2505.24688","title":"Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration","created":"2025-05-30","cited_by_count":7,"area":"lr"},{"id":"2504.11364","title":"Offline Learning and Forgetting for Reasoning with Large Language Models","created":"2025-04-15","cited_by_count":4,"area":"lr"},{"id":"2601.09929","title":"Hallucination Detection and Mitigation in Large Language Models","created":"2026-01-14","cited_by_count":4,"area":"lr"},{"id":"2404.03577","title":"Untangle the KNOT: Interweaving Conflicting Knowledge and Reasoning Skills in Large Language Models","created":"2024-04-04","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":"2412.20297","title":"FaGeL: Fabric LLMs Agent empowered Embodied Intelligence Evolution with Autonomous Human-Machine Collaboration","created":"2024-12-28","cited_by_count":2,"area":"lr"},{"id":"2305.04522","title":"Event Knowledge Incorporation with Posterior Regularization for Event-Centric Question Answering","created":"2023-05-08","cited_by_count":1,"area":"lr"},{"id":"2406.02804","title":"ACCORD: Closing the Commonsense Measurability Gap","created":"2024-06-04","cited_by_count":1,"area":"lr"},{"id":"2602.01689","title":"What LLMs Think When You Don't Tell Them What to Think About?","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2605.07137","title":"Adaptive Negative Reinforcement for LLM Reasoning:Dynamically Balancing Correction and Diversity in RLVR","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2607.07976","title":"When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning","created":"2026-07-08","cited_by_count":1,"area":"lr"},{"id":"2609.13520","title":"From Token Probabilities to Semantic Constraints: Towards Declarative Probabilistic Evaluation of Language Models","created":"2026-09-11","cited_by_count":1,"area":"lr"},{"id":"2511.06023","title":"Multi-Reward GRPO Fine-Tuning for De-biasing Large Language Models: A Study Based on Chinese-Context Discrimination Data","created":"2025-11-08","cited_by_count":0,"area":"lr"},{"id":"2512.22545","title":"Self-Rewarded Multimodal Coherent Reasoning Across Diverse Visual Domains","created":"2025-12-27","cited_by_count":0,"area":"lr"},{"id":"2603.14745","title":"CAMD: Coverage-Aware Multimodal Decoding for Efficient Reasoning of Multimodal Large Language Models","created":"2026-03-16","cited_by_count":0,"area":"lr"},{"id":"2605.22211","title":"CLORE: Content-Level Optimization for Reasoning Efficiency","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2606.16700","title":"Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2608.12781","title":"Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs","created":"2026-08-13","cited_by_count":0,"area":"lr"},{"id":"2609.20563","title":"Reasoning Quality Matters: Combating Reasoning Collapse in LLM-based Embedding Learning","created":"2026-09-17","cited_by_count":0,"area":"lr"},{"id":"2610.11366","title":"SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.18127","title":"Monitoring latent reasoning in looped language models","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}