English(EN) Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation

EVOL-RL 方法在无标签情况下增强语言模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-27 04:00

研究人员开发了 EVOL-RL，一种无需依赖外部标签即可改进语言模型的新颖方法。该方法解决了“选择诱导多样性崩溃”的问题，即自我选择会缩小模型的响应池。EVOL-RL 通过使用多数投票进行稳定选择和基于嵌入的新颖性来细化信用，同时熵正则化和不对称裁剪有助于维持多样化的推广。实验表明，EVOL-RL 在 AIME24 和 AIME25 数学竞赛等任务上的性能显著提高，优于基线方法。 AI

影响该方法可以通过减少对标记数据的依赖，从而实现更高效的 LLM 训练，并可能加速开发周期。

排序理由该集群包含一篇 arXiv 论文，详细介绍了演进语言模型的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

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

本文如何被排名

Signal score: 8 / 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 arXiv 论文，详细介绍了演进语言模型的新方法。[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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Yujun Zhou, Zhenwen Liang, Haolin Liu, Wenhao Yu, Kishan Panaganti, Linfeng Song, Dian Yu, Xiangliang Zhang, Haitao Mi, Dong Yu · 2026-10-27 04:00

无需标签的语言模型演进：多数驱动选择，新颖促进变异

arXiv:2509.15194v4 Announce Type: replace-cross Abstract: Large language models (LLMs) can improve through reinforcement learning with verifiable rewards (RLVR), but many settings lack reference answers or external verifiers. Label-free self-improvement instead constructs trainin…

本文如何被排名

报道来源 [1]

无需标签的语言模型演进：多数驱动选择，新颖促进变异

相关实体

相关话题