PulseAugur
实时 09:49:18
English(EN) Failure-Guided Co-Evolution of Prompts and Training Data

新框架FORGE协同进化LLM的提示词和训练数据

研究人员开发了一个新颖的框架FORGE,该框架可同时优化语言模型的提示词并合成新的训练数据。这种方法解决了现有方法仅修改提示词而保持训练数据不变的局限性,这可能导致未探索的失败情况。通过将每次失败视为提示词修改和数据合成的信号,FORGE通过四种突变策略生成新的训练实例。在八个基准测试中进行测试,FORGE在总体得分上显示出显著的改进,并在后续研究中显示出积极的迁移效应。 AI

影响 这项研究可能带来更有效和更高效的训练和微调大型语言模型的方法,从而可能提高它们在更广泛任务上的性能。

排序理由 该集群包含一篇详细介绍改进语言模型新框架的研究论文。[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FORGE协同进化LLM的提示词和训练数据

本文如何被排名

Signal score
12 / 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改进语言模型新框架的研究论文。[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
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

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) · Tianyu Yuan, Zhuzhong Qian ·

    基于失败的提示词和训练数据协同进化

    arXiv:2609.15209v1 Announce Type: cross Abstract: Automatic prompt optimization (APO) improves language-model programs by revising prompts from task feedback, yet it typically holds its training data fixed. Repeatedly optimizing against the same instances confines feedback to wea…