@inproceedings{kang-etal-2026-wsdpo,
title = "{WSDPO}: A Generative Word Sense Disambiguation Framework with Chain-of-Thought and Preference Optimization",
author = "Kang, Kunpeng and
Li, Shuaimin and
Zhang, Kaiyuan and
Zhang, Luyang and
Si, Jiasheng and
Xu, Bing and
Chen, Kehai and
Yang, Muyun and
Lu, Wenpeng",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1610/",
pages = "34870--34889",
ISBN = "979-8-89176-390-6",
abstract = "Word sense disambiguation (WSD) is a foundational task in natural language processing. Recent research has reformulated WSD for large language models (LLMs) as a generative task, where the model produces a definition to convey the intended meaning of an ambiguous word in context.In practice, most existing approaches implement this formulation through straightforward supervised fine-tuning, which tends to prioritize superficial context-to-gloss memorization over true contextual sense discrimination, leading to degraded performance on less frequent senses (LFS), particularly in unseen settings.To address this issue, we propose WSDPO, a training framework for generative WSD with chain-of-thought (CoT) and preference optimization. WSDPO consists of three stages: (1) disambiguation-aware CoT construction, which produces training data containing explicit disambiguation steps for the later stage;(2) disambiguation-guided supervised fine-tuning, which explicitly trains the model to discriminate word sense before generating the final definition; and(3) preference-based optimization, which further strengthens the model{'}s ability to generate sense-faithful definitions by optimizing it using preference pairs constructed from multiple sampled CoT outputs.Extensive experiments across benchmark datasets and multiple backbone LLMs demonstrate that WSDPO achieves substantial performance gains on rare and unseen settings, and exhibits strong generalization in standard evaluation settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kang-etal-2026-wsdpo">
<titleInfo>
<title>WSDPO: A Generative Word Sense Disambiguation Framework with Chain-of-Thought and Preference Optimization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kunpeng</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuaimin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaiyuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luyang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiasheng</namePart>
<namePart type="family">Si</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kehai</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muyun</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenpeng</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Word sense disambiguation (WSD) is a foundational task in natural language processing. Recent research has reformulated WSD for large language models (LLMs) as a generative task, where the model produces a definition to convey the intended meaning of an ambiguous word in context.In practice, most existing approaches implement this formulation through straightforward supervised fine-tuning, which tends to prioritize superficial context-to-gloss memorization over true contextual sense discrimination, leading to degraded performance on less frequent senses (LFS), particularly in unseen settings.To address this issue, we propose WSDPO, a training framework for generative WSD with chain-of-thought (CoT) and preference optimization. WSDPO consists of three stages: (1) disambiguation-aware CoT construction, which produces training data containing explicit disambiguation steps for the later stage;(2) disambiguation-guided supervised fine-tuning, which explicitly trains the model to discriminate word sense before generating the final definition; and(3) preference-based optimization, which further strengthens the model’s ability to generate sense-faithful definitions by optimizing it using preference pairs constructed from multiple sampled CoT outputs.Extensive experiments across benchmark datasets and multiple backbone LLMs demonstrate that WSDPO achieves substantial performance gains on rare and unseen settings, and exhibits strong generalization in standard evaluation settings.</abstract>
<identifier type="citekey">kang-etal-2026-wsdpo</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1610/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>34870</start>
<end>34889</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WSDPO: A Generative Word Sense Disambiguation Framework with Chain-of-Thought and Preference Optimization
%A Kang, Kunpeng
%A Li, Shuaimin
%A Zhang, Kaiyuan
%A Zhang, Luyang
%A Si, Jiasheng
%A Xu, Bing
%A Chen, Kehai
%A Yang, Muyun
%A Lu, Wenpeng
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F kang-etal-2026-wsdpo
%X Word sense disambiguation (WSD) is a foundational task in natural language processing. Recent research has reformulated WSD for large language models (LLMs) as a generative task, where the model produces a definition to convey the intended meaning of an ambiguous word in context.In practice, most existing approaches implement this formulation through straightforward supervised fine-tuning, which tends to prioritize superficial context-to-gloss memorization over true contextual sense discrimination, leading to degraded performance on less frequent senses (LFS), particularly in unseen settings.To address this issue, we propose WSDPO, a training framework for generative WSD with chain-of-thought (CoT) and preference optimization. WSDPO consists of three stages: (1) disambiguation-aware CoT construction, which produces training data containing explicit disambiguation steps for the later stage;(2) disambiguation-guided supervised fine-tuning, which explicitly trains the model to discriminate word sense before generating the final definition; and(3) preference-based optimization, which further strengthens the model’s ability to generate sense-faithful definitions by optimizing it using preference pairs constructed from multiple sampled CoT outputs.Extensive experiments across benchmark datasets and multiple backbone LLMs demonstrate that WSDPO achieves substantial performance gains on rare and unseen settings, and exhibits strong generalization in standard evaluation settings.
%U https://aclanthology.org/2026.acl-long.1610/
%P 34870-34889
Markdown (Informal)
[WSDPO: A Generative Word Sense Disambiguation Framework with Chain-of-Thought and Preference Optimization](https://aclanthology.org/2026.acl-long.1610/) (Kang et al., ACL 2026)
ACL
- Kunpeng Kang, Shuaimin Li, Kaiyuan Zhang, Luyang Zhang, Jiasheng Si, Bing Xu, Kehai Chen, Muyun Yang, and Wenpeng Lu. 2026. WSDPO: A Generative Word Sense Disambiguation Framework with Chain-of-Thought and Preference Optimization. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 34870–34889, San Diego, California, United States. Association for Computational Linguistics.