@inproceedings{yang-etal-2025-multi,
title = "Multi-perspective Preference Alignment of {LLM}s for Programming-Community Question Answering",
author = "Yang, Hongyu and
Hou, Jiahui and
He, Liyang and
Li, Rui",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.113/",
pages = "1667--1682",
abstract = "Programming-Community Question Answering (PCQA) aims to tackle issues through generating functional code and guiding descriptions. It involves multiple candidates, with different users having varying preferences for them. Additionally, one may contain outdated APIs. These undoubtedly present a challenge for responsing that meet user preferences. Recently, Reinforcement Learning from Human Feedback demonstrates its ability to precisely control the behavior of large language models (LLMs) to yield human-like responses. However, applying it to LLMs in domain-specific PCQA remains unexplored. In this work, we propose Multi-perspective Preference Alignment for Programming-Community Question Answering to generate user-centric responses, called MupPCQA. It includes three stages: Preference Standardization to control content quality, Preference Integration to consider diverse user tendencies, Preference Timeliness Mitigation to alleviate outdated answers. Extensive experiments on a high-quality, real-world PCQA dataset validate its accuracy and preference. Compared to its base model, MupPCQA shows an improvement of nearly 11{\%} in BLEU, with increases of 20{\%} and 17.5{\%} in BERTScore and CodeBERTScore."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2025-multi">
<titleInfo>
<title>Multi-perspective Preference Alignment of LLMs for Programming-Community Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongyu</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiahui</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liyang</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Programming-Community Question Answering (PCQA) aims to tackle issues through generating functional code and guiding descriptions. It involves multiple candidates, with different users having varying preferences for them. Additionally, one may contain outdated APIs. These undoubtedly present a challenge for responsing that meet user preferences. Recently, Reinforcement Learning from Human Feedback demonstrates its ability to precisely control the behavior of large language models (LLMs) to yield human-like responses. However, applying it to LLMs in domain-specific PCQA remains unexplored. In this work, we propose Multi-perspective Preference Alignment for Programming-Community Question Answering to generate user-centric responses, called MupPCQA. It includes three stages: Preference Standardization to control content quality, Preference Integration to consider diverse user tendencies, Preference Timeliness Mitigation to alleviate outdated answers. Extensive experiments on a high-quality, real-world PCQA dataset validate its accuracy and preference. Compared to its base model, MupPCQA shows an improvement of nearly 11% in BLEU, with increases of 20% and 17.5% in BERTScore and CodeBERTScore.</abstract>
<identifier type="citekey">yang-etal-2025-multi</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.113/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>1667</start>
<end>1682</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-perspective Preference Alignment of LLMs for Programming-Community Question Answering
%A Yang, Hongyu
%A Hou, Jiahui
%A He, Liyang
%A Li, Rui
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F yang-etal-2025-multi
%X Programming-Community Question Answering (PCQA) aims to tackle issues through generating functional code and guiding descriptions. It involves multiple candidates, with different users having varying preferences for them. Additionally, one may contain outdated APIs. These undoubtedly present a challenge for responsing that meet user preferences. Recently, Reinforcement Learning from Human Feedback demonstrates its ability to precisely control the behavior of large language models (LLMs) to yield human-like responses. However, applying it to LLMs in domain-specific PCQA remains unexplored. In this work, we propose Multi-perspective Preference Alignment for Programming-Community Question Answering to generate user-centric responses, called MupPCQA. It includes three stages: Preference Standardization to control content quality, Preference Integration to consider diverse user tendencies, Preference Timeliness Mitigation to alleviate outdated answers. Extensive experiments on a high-quality, real-world PCQA dataset validate its accuracy and preference. Compared to its base model, MupPCQA shows an improvement of nearly 11% in BLEU, with increases of 20% and 17.5% in BERTScore and CodeBERTScore.
%U https://aclanthology.org/2025.coling-main.113/
%P 1667-1682
Markdown (Informal)
[Multi-perspective Preference Alignment of LLMs for Programming-Community Question Answering](https://aclanthology.org/2025.coling-main.113/) (Yang et al., COLING 2025)
ACL