用 DPO 偏好优化改进定义生成：欧盟机构可持续金融披露中的语义变化检测

Preference Optimization Improves Definition Generation: Semantic Change in EU Institutional Sustainable Finance Disclosures

AI 导读

研究显示，用 Direct Preference Optimization（DPO）微调类词典定义生成器，可缓解同一词义被拆成过多定义的问题。方法在精选的学术 LSCD 基准上做了定量评测，并在欧盟发展金融项目文档中审计可持续金融术语的历时变化。所有模型、代码与预测结果均已公开。

正文

View PDF HTML (experimental)

Abstract:Dictionary-like definition generators are known to be useful for lexical semantic change detection (LSCD). However, they suffer from overly granular sense distribution, producing excessive number of definitions for one and the same lexical sense. In this work, we show that fine-tuning with Direct Preference Optimization (DPO) helps to overcome this problem. We test our approach both quantitatively on a curated academic LSCD benchmark and qualitatively on real-world data for a practical task of auditing diachronic changes in sustainability terminology within project documentation of EU development finance. All models, code and predictions produced in this study are publicly available at this https URL.

Comments:	the 5th NLP4PI (NLP for Positive Impact) Workshop@EMNLP 2026
Subjects:	Computation and Language (cs.CL)
Cite as:	arXiv:2610.33357 [cs.CL]
	(or arXiv:2610.33357v1 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2610.33357 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Mariia Fedorova [view email]
[v1] Fri, 23 Oct 2026 22:54:18 UTC (36 KB)

来源：arXiv cs.CL · arxiv.org