{"total":13,"rows":[{"id":"2405.20304","title":"Group Robust Preference Optimization in Reward-free RLHF","created":"2024-05-30","cited_by_count":95,"area":"lr"},{"id":"2602.05547","title":"Multi-Task GRPO: Reliable LLM Reasoning Across Tasks","created":"2026-02-05","cited_by_count":14,"area":"lr"},{"id":"2601.19280","title":"Group Distributionally Robust Optimization-Driven Reinforcement Learning for LLM Reasoning","created":"2026-01-27","cited_by_count":12,"area":"lr"},{"id":"2511.18123","title":"Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models","created":"2025-11-22","cited_by_count":7,"area":"lr"},{"id":"2602.23777","title":"Reasoning-Driven Multimodal LLM for Domain Generalization","created":"2026-02-27","cited_by_count":7,"area":"lr"},{"id":"2410.04492","title":"Interpret Your Decision: Logical Reasoning Regularization for Generalization in Visual Classification","created":"2024-10-06","cited_by_count":5,"area":"lr"},{"id":"2511.15242","title":"Trustworthy and Fair SkinGPT-R1 for Democratizing Dermatological Reasoning across Diverse Ethnicities","created":"2025-11-19","cited_by_count":3,"area":"lr"},{"id":"2505.21598","title":"Rethinking Data Mixture for Large Language Models: A Comprehensive Survey and New Perspectives","created":"2025-05-27","cited_by_count":2,"area":"lr"},{"id":"2603.20899","title":"Mitigating Shortcut Reasoning in Language Models: A Gradient-Aware Training Approach","created":"2026-03-21","cited_by_count":2,"area":"lr"},{"id":"2511.21397","title":"Understanding the Effects of Distractors on Reasoning Vision-Language Models","created":"2025-11-26","cited_by_count":1,"area":"lr"},{"id":"2606.05025","title":"Invariant Gradient Alignment for Robust Reasoning Distillation","created":"2026-06-03","cited_by_count":1,"area":"lr"},{"id":"2607.14349","title":"HABIB_TAZ at SemEval-2026 Task 11: Disentangling Formal Logic from Content via Synthetic Training and Multi-Objective Optimization","created":"2026-07-15","cited_by_count":0,"area":"lr"},{"id":"2609.16268","title":"Spurious Tool Use: When RL Agents Learn the Wrong Reason to Act","created":"2026-09-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}