@inproceedings{wang-etal-2025-puer,
title = "{PUER}: Boosting Few-shot Positive-Unlabeled Entity Resolution with Reinforcement Learning",
author = "Wang, Yaoshu and
Yan, Mengyi and
Wang, Wei",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.1336/",
pages = "24567--24579",
ISBN = "979-8-89176-335-7",
abstract = "Entity resolution is a fundamental problem in data management that aims to identify all duplicate entries within collections of multi-attribute tuples. Most existing works focus on supervised learning, relying on large amounts of high-quality labeled data, including both positive and negative tuple pairs that are meticulously prepared. However, in reality, the manual annotation process is labor-intensive; in particular, selecting high-quality negative data for labeling is both important and challenging. In this paper, we propose an end-to-end ER solution, PUER, to address low-resource entity resolution (ER) by leveraging Large Language Models (LLMs) in a Positive-Unlabeled (PU) learning setting, where only a small number of positively labeled examples, e.g., 50, and unlabeled data are provided. Unlike directly fine-tuning LLMs in a supervised manner, we solve the entity matching task using reinforcement learning and propose a self-adaptive reward function in the process of RL. To enhance performance, we design an iterative workflow based on the co-training mechanism that fully utilizes entity blocking component to assist the entity matching. This workflow aims to improve the robustness and quality of pseudo-labels so that the performance of entity matching improves. Comprehensive experimental results on various benchmark datasets demonstrate the superiority of PUER. Full version and code are available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2025-puer">
<titleInfo>
<title>PUER: Boosting Few-shot Positive-Unlabeled Entity Resolution with Reinforcement Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaoshu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengyi</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Entity resolution is a fundamental problem in data management that aims to identify all duplicate entries within collections of multi-attribute tuples. Most existing works focus on supervised learning, relying on large amounts of high-quality labeled data, including both positive and negative tuple pairs that are meticulously prepared. However, in reality, the manual annotation process is labor-intensive; in particular, selecting high-quality negative data for labeling is both important and challenging. In this paper, we propose an end-to-end ER solution, PUER, to address low-resource entity resolution (ER) by leveraging Large Language Models (LLMs) in a Positive-Unlabeled (PU) learning setting, where only a small number of positively labeled examples, e.g., 50, and unlabeled data are provided. Unlike directly fine-tuning LLMs in a supervised manner, we solve the entity matching task using reinforcement learning and propose a self-adaptive reward function in the process of RL. To enhance performance, we design an iterative workflow based on the co-training mechanism that fully utilizes entity blocking component to assist the entity matching. This workflow aims to improve the robustness and quality of pseudo-labels so that the performance of entity matching improves. Comprehensive experimental results on various benchmark datasets demonstrate the superiority of PUER. Full version and code are available.</abstract>
<identifier type="citekey">wang-etal-2025-puer</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.1336/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>24567</start>
<end>24579</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PUER: Boosting Few-shot Positive-Unlabeled Entity Resolution with Reinforcement Learning
%A Wang, Yaoshu
%A Yan, Mengyi
%A Wang, Wei
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F wang-etal-2025-puer
%X Entity resolution is a fundamental problem in data management that aims to identify all duplicate entries within collections of multi-attribute tuples. Most existing works focus on supervised learning, relying on large amounts of high-quality labeled data, including both positive and negative tuple pairs that are meticulously prepared. However, in reality, the manual annotation process is labor-intensive; in particular, selecting high-quality negative data for labeling is both important and challenging. In this paper, we propose an end-to-end ER solution, PUER, to address low-resource entity resolution (ER) by leveraging Large Language Models (LLMs) in a Positive-Unlabeled (PU) learning setting, where only a small number of positively labeled examples, e.g., 50, and unlabeled data are provided. Unlike directly fine-tuning LLMs in a supervised manner, we solve the entity matching task using reinforcement learning and propose a self-adaptive reward function in the process of RL. To enhance performance, we design an iterative workflow based on the co-training mechanism that fully utilizes entity blocking component to assist the entity matching. This workflow aims to improve the robustness and quality of pseudo-labels so that the performance of entity matching improves. Comprehensive experimental results on various benchmark datasets demonstrate the superiority of PUER. Full version and code are available.
%U https://aclanthology.org/2025.findings-emnlp.1336/
%P 24567-24579
Markdown (Informal)
[PUER: Boosting Few-shot Positive-Unlabeled Entity Resolution with Reinforcement Learning](https://aclanthology.org/2025.findings-emnlp.1336/) (Wang et al., Findings 2025)
ACL