PulseAugur
实时 10:20:57
English(EN) Fishing Out Free Riders: Shapley-Based Reward Attribution for Parallel Reasoning via Reinforcement Learning

新框架使用 Shapley 值归因大型语言模型推理路径贡献

研究人员开发了一个名为 Parallel Shapley 的新强化学习框架,以解决大型语言模型(LLMs)多步推理中的奖励归因挑战。该方法将每个推理路径视为合作博弈中的一个参与者,使用 Shapley 值量化个体贡献,并使用带有蒙特卡洛采样的生成奖励模型进行有效近似。在数学推理基准上的实验表明,与现有方法相比,Parallel Shapley 能够实现更稳定和可解释的训练,有效识别和惩罚冗余或有害的推理路径。 AI

影响 该框架有望提高 LLMs 在复杂推理任务训练中的效率和可解释性。

排序理由 该集群包含一篇详细介绍 LLM 推理新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新框架使用 Shapley 值归因大型语言模型推理路径贡献

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇详细介绍 LLM 推理新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
48 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Wentao Zhang, Haoyu Zhang, Xinke Jiang, Yuxuan Cheng, Yuhan Pan, Miao Li, Zhipeng Qiao, Tao Feng, Zhen Tao, Dengji Zhao ·

    钓出“搭便车者”:基于 Shapley 的强化学习并行推理奖励归因

    arXiv:2607.18979v1 Announce Type: new Abstract: Large Language Models (LLMs) excel at multi-step reasoning, yet current parallel reasoning approaches often fail to distinguish the contributions of individual reasoning paths. Many paths may be redundant, misleading, or even detrim…