arXiv 2610.17771 · cs.CL · 2026-10-13
Many Right Answers, One Training Example: Removing Responder Noise from GRPO for LLM Recommenders
Xin Li, Hao Jiang, Jinghao Guo, Weisi Lin, Chau Yuen
Nanyang Technological University
在最新榜 #259 本站收录于 2026-10-21
一句话要点
ReMaRk 让大模型推荐器的 GRPO 训练对所有回复的并集打分，消除随机抽一个回复带来的噪声。
ReMaRk scores recommendation lists against the union of all replies, removing responder noise from GRPO training of LLM recommenders.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：强化学习
- Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation ▲218
- Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight ▲189
- LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches ▲152
- Sharpening Tax in Post-Training ▲111
- RULER: Instance-aware Rubric Rewards for SVG Generation ▲104
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。