English(EN) Categorical Prior Lock-in: Why In-Context Learning Fails for Structured Data

新研究揭示上下文学习在结构化数据上的局限性

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-10 11:41

一篇新的研究论文识别出一种名为“分类先验锁定”的现象，该现象限制了大型语言模型在生成结构化数据时上下文学习（ICL）的有效性。研究发现，虽然ICL可以提高数值准确性，但在表格数据中复制稀有类别方面存在困难。LoRA等参数高效微调方法可以克服这一点，但会带来记忆化和输出不稳定的风险。 AI

影响识别出LLM在结构化数据生成方面的关键适应性局限性，可能影响依赖ICL的应用。

排序理由该集群包含一篇详细介绍LLM行为新发现的学术论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

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: Research; 该集群包含一篇详细介绍LLM行为新发现的学术论文。
Source corroboration: 2 independent sources; Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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: 95 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。

arXiv cs.AI TIER_1 English(EN) · Antonio Pelusi, Stefano Braghin, Alberto Trombetta · 2026-06-11 04:00

分类先验锁定：为何上下文学习在结构化数据上会失败

arXiv:2606.11961v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as conditional generators for structured data, relying on in-context learning (ICL) to adapt to new distributions without parameter updates. We investigate the limits of ICL for s…
arXiv cs.AI TIER_1 English(EN) · Alberto Trombetta · 2026-06-10 11:41

分类先验锁定：为何上下文学习在结构化数据上会失败

Large language models (LLMs) are increasingly used as conditional generators for structured data, relying on in-context learning (ICL) to adapt to new distributions without parameter updates. We investigate the limits of ICL for structured generation under distribution mismatch, …