[论文] An Exploration-Analysis-Disambiguation Reasoning Framework for Word Se...

## 论文概要 **研究领域**: NLP **作者**: Junyu Lu, Yanan Zheng, Chen Gong, Yibo Zhang, Shengnan Li, Yining Zhang, Daimeng Wei, Zhiqiang Zhang, Jiajun Zhang **发布时间**: 2026-03-05 **arXiv**: [2603.05400](https://arxiv.org/abs/2603.05400) ## 中文摘要 词义消歧（WSD）仍然是自然语言处理（NLP）中的一个关键挑战，特别是在处理罕见或模糊词语时，仅靠上下文是不够的。虽然大语言模型（LLM）已显示出前景，但它们在 WSD 任务上的性能往往受到依赖频繁语义偏见而非上下文分析倾向的阻碍。本文提出了探索-分析-消歧（EAD）推理框架，使低参数 LLM 能够为 WSD 执行显式推理。该框架包括三个阶段：探索潜在语义、分析上下文相关性、最终消歧。实验表明，该方法在标准基准上显著提高了 WSD 性能，同时使用的模型参数量不到 100 亿。 ## 原文摘要 Word Sense Disambiguation (WSD) remains a key challenge in Natural Language Processing (NLP), especially when dealing with rare or ambiguous words where context alone is insufficient. While large language models (LLMs) have shown promise, their performance on WSD tasks is often hindered by their tendency to rely on frequent sense biases rather than contextual analysis. In this paper, we propose an Exploration-Analysis-Disambiguation (EAD) reasoning framework that enables low-parameter LLMs to perform explicit reasoning for WSD. The framework consists of three stages: exploration of potential senses, analysis of contextual relevance, and final disambiguation. Our experiments show that this approach significantly improves WSD performance on standard benchmarks while using models with fewer t... --- *自动采集于 2026-03-07* #论文 #arXiv #NLP #小凯