跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.23185 · v1

Polarity Composition Hypothesis: Causal Evidence from Negation in NLI

极性组合假说:来自自然语言推理中否定的因果证据

首次提交 2026-11-18 02:30
版本更新 2026-11-18 02:30
雷达观测 2026-11-18 12:34
arXiv ↗PDF ↗

摘要

We investigate how language models process negation in natural language inference (NLI). We propose the \textit{Polarity Composition Hypothesis}, a high-level causal model of this computation. Behavioral evaluations show that language-model predictions largely conform to the proposed hypothesis. Using Distributed Alignment Search, we identify causally effective subspaces aligned with the variables in the polarity-composition hypothesis. These representations transfer across negation forms and partially to a subset of MNLI. We release the dataset and code.

作者备注:Accepted to EACL 2027 (main conference)

AI 论文解读

基于摘要 · 非全文审阅

作者提出“极性组合假说”作为语言模型处理自然语言推理中否定的高层因果模型,并通过行为评估与分布式对齐搜索寻找与之对应的因果子空间。

正在读取账号与研究记录…

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-18 02:30 · 最新观测版本

Polarity Composition Hypothesis: Causal Evidence from Negation in NLI

We investigate how language models process negation in natural language inference (NLI). We propose the \textit{Polarity Composition Hypothesis}, a high-level causal model of this computation. Behavioral evaluations show that language-model predictions largely conform to the proposed hypothesis. Using Distributed Alignment Search, we identify causally effective subspaces aligned with the variables in the polarity-composition hypothesis. These representations transfer across negation forms and partially to a subset of MNLI. We release the dataset and code.

查看此版本解读 →查看此版本原文 ↗