@inproceedings{ok-etal-2025-synthetic,
title = "Synthetic Paths to Integral Truth: Mitigating Hallucinations Caused by Confirmation Bias with Synthetic Data",
author = "Ok, Changwon and
Lee, Eunkyeong and
Oh, Dongsuk",
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.347/",
pages = "5168--5180",
abstract = "Recently, large language models (LLMs) have made significant progress through retrieval-augmented generation (RAG) and preference learning. However, they still exhibit issues such as confirmation bias, the tendency to favor information that confirms one`s beliefs, which remains largely unexplored in current research. In this paper, we propose a novel approach to mitigate confirmation bias-induced hallucination in LLMs through a synthetic data construction pipeline and Direct Preference Optimization (DPO) training. Our method enhances the integration of diverse and complementary information from multiple passages retrieved by RAG, enabling more balanced and accurate reasoning. Experimental results demonstrate significant improvements in response accuracy and reduced hallucination on benchmarks such as Natural Questions Open and HaluBench. These findings suggest that our approach effectively mitigates confirmation bias in long-context question answering, with potential applications to other NLP tasks. We release our data, and evaluation/train code for public access.3]\url{https://github.com/OccasionallyNLP/Synthetic-Paths-to-Integral-Truth.git}"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ok-etal-2025-synthetic">
<titleInfo>
<title>Synthetic Paths to Integral Truth: Mitigating Hallucinations Caused by Confirmation Bias with Synthetic Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Changwon</namePart>
<namePart type="family">Ok</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunkyeong</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongsuk</namePart>
<namePart type="family">Oh</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>Recently, large language models (LLMs) have made significant progress through retrieval-augmented generation (RAG) and preference learning. However, they still exhibit issues such as confirmation bias, the tendency to favor information that confirms one‘s beliefs, which remains largely unexplored in current research. In this paper, we propose a novel approach to mitigate confirmation bias-induced hallucination in LLMs through a synthetic data construction pipeline and Direct Preference Optimization (DPO) training. Our method enhances the integration of diverse and complementary information from multiple passages retrieved by RAG, enabling more balanced and accurate reasoning. Experimental results demonstrate significant improvements in response accuracy and reduced hallucination on benchmarks such as Natural Questions Open and HaluBench. These findings suggest that our approach effectively mitigates confirmation bias in long-context question answering, with potential applications to other NLP tasks. We release our data, and evaluation/train code for public access.3]https://github.com/OccasionallyNLP/Synthetic-Paths-to-Integral-Truth.git</abstract>
<identifier type="citekey">ok-etal-2025-synthetic</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.347/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>5168</start>
<end>5180</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Synthetic Paths to Integral Truth: Mitigating Hallucinations Caused by Confirmation Bias with Synthetic Data
%A Ok, Changwon
%A Lee, Eunkyeong
%A Oh, Dongsuk
%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 ok-etal-2025-synthetic
%X Recently, large language models (LLMs) have made significant progress through retrieval-augmented generation (RAG) and preference learning. However, they still exhibit issues such as confirmation bias, the tendency to favor information that confirms one‘s beliefs, which remains largely unexplored in current research. In this paper, we propose a novel approach to mitigate confirmation bias-induced hallucination in LLMs through a synthetic data construction pipeline and Direct Preference Optimization (DPO) training. Our method enhances the integration of diverse and complementary information from multiple passages retrieved by RAG, enabling more balanced and accurate reasoning. Experimental results demonstrate significant improvements in response accuracy and reduced hallucination on benchmarks such as Natural Questions Open and HaluBench. These findings suggest that our approach effectively mitigates confirmation bias in long-context question answering, with potential applications to other NLP tasks. We release our data, and evaluation/train code for public access.3]https://github.com/OccasionallyNLP/Synthetic-Paths-to-Integral-Truth.git
%U https://aclanthology.org/2025.coling-main.347/
%P 5168-5180
Markdown (Informal)
[Synthetic Paths to Integral Truth: Mitigating Hallucinations Caused by Confirmation Bias with Synthetic Data](https://aclanthology.org/2025.coling-main.347/) (Ok et al., COLING 2025)
ACL