@inproceedings{wan-etal-2026-insideout,
title = "{I}nside{O}ut: Measuring and Mitigating Insider{--}Outsider Bias in Interview Script Generation",
author = "Wan, Yixin and
Chen, Xingrun and
Chang, Kai-Wei",
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.1094/",
doi = "10.18653/v1/2026.acl-long.1094",
pages = "23864--23883",
ISBN = "979-8-89176-390-6",
abstract = "Advancements in Large language models (LLMs) have enabled a variety of downstream applications like story and interview script generation.However, recent research raised concerns about culture-related fairness issues in LLM-generated content.In this work, we identify and systematically investigate LLMs' \textbf{insider-outsider bias}, a phenomenon where models position themselves as ``insiders'' of mainstream cultures during generation while externalizing less dominant cultures.We propose the \textit{\textbf{InsideOut}} benchmark with 4,000 generation prompts and three evaluation metrics to quantify this bias through a \textit{culturally situated interview script generation} task, in which an LLM is positioned as a reporter interviewing local people across 10 diverse cultures.Empirical evaluation on 5 state-of-the-art LLMs reveals that while models adopt insider tones in over 88{\%} US-contexted scripts on average, they disproportionately default to ``outsider'' stances for non-Western cultures.To mitigate these biases, we propose \textit{2 inference-time methods}: a baseline prompt-based \textbf{Fairness Intervention Pillars (FIP)} method, and a structured \textbf{Mitigation via Fairness Agents (MFA)} framework consisting of a Single-Agent (MFA-SA), a Hierarchical-Agent (MFA-HA), and an autonomous Agentic Planning (MFA-Plan) pipeline.Empirical results demonstrate that agent-based MFA methods achieve outstanding and robust performance in mitigating the insider-outsider bias:For instance, on the Cultural Alignment Gap (CAG) metric, \textit{MFA-SA reduces bias in Llama model by 89.70 {\%} and MFA-HA mitigates bias in Qwen by 82.54{\%}}.These findings showcase the effectiveness of agent-based methods as a promising direction for mitigating biases in generative LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wan-etal-2026-insideout">
<titleInfo>
<title>InsideOut: Measuring and Mitigating Insider–Outsider Bias in Interview Script Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yixin</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingrun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</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>Advancements in Large language models (LLMs) have enabled a variety of downstream applications like story and interview script generation.However, recent research raised concerns about culture-related fairness issues in LLM-generated content.In this work, we identify and systematically investigate LLMs’ insider-outsider bias, a phenomenon where models position themselves as “insiders” of mainstream cultures during generation while externalizing less dominant cultures.We propose the InsideOut benchmark with 4,000 generation prompts and three evaluation metrics to quantify this bias through a culturally situated interview script generation task, in which an LLM is positioned as a reporter interviewing local people across 10 diverse cultures.Empirical evaluation on 5 state-of-the-art LLMs reveals that while models adopt insider tones in over 88% US-contexted scripts on average, they disproportionately default to “outsider” stances for non-Western cultures.To mitigate these biases, we propose 2 inference-time methods: a baseline prompt-based Fairness Intervention Pillars (FIP) method, and a structured Mitigation via Fairness Agents (MFA) framework consisting of a Single-Agent (MFA-SA), a Hierarchical-Agent (MFA-HA), and an autonomous Agentic Planning (MFA-Plan) pipeline.Empirical results demonstrate that agent-based MFA methods achieve outstanding and robust performance in mitigating the insider-outsider bias:For instance, on the Cultural Alignment Gap (CAG) metric, MFA-SA reduces bias in Llama model by 89.70 % and MFA-HA mitigates bias in Qwen by 82.54%.These findings showcase the effectiveness of agent-based methods as a promising direction for mitigating biases in generative LLMs.</abstract>
<identifier type="citekey">wan-etal-2026-insideout</identifier>
<identifier type="doi">10.18653/v1/2026.acl-long.1094</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1094/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>23864</start>
<end>23883</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T InsideOut: Measuring and Mitigating Insider–Outsider Bias in Interview Script Generation
%A Wan, Yixin
%A Chen, Xingrun
%A Chang, Kai-Wei
%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 wan-etal-2026-insideout
%X Advancements in Large language models (LLMs) have enabled a variety of downstream applications like story and interview script generation.However, recent research raised concerns about culture-related fairness issues in LLM-generated content.In this work, we identify and systematically investigate LLMs’ insider-outsider bias, a phenomenon where models position themselves as “insiders” of mainstream cultures during generation while externalizing less dominant cultures.We propose the InsideOut benchmark with 4,000 generation prompts and three evaluation metrics to quantify this bias through a culturally situated interview script generation task, in which an LLM is positioned as a reporter interviewing local people across 10 diverse cultures.Empirical evaluation on 5 state-of-the-art LLMs reveals that while models adopt insider tones in over 88% US-contexted scripts on average, they disproportionately default to “outsider” stances for non-Western cultures.To mitigate these biases, we propose 2 inference-time methods: a baseline prompt-based Fairness Intervention Pillars (FIP) method, and a structured Mitigation via Fairness Agents (MFA) framework consisting of a Single-Agent (MFA-SA), a Hierarchical-Agent (MFA-HA), and an autonomous Agentic Planning (MFA-Plan) pipeline.Empirical results demonstrate that agent-based MFA methods achieve outstanding and robust performance in mitigating the insider-outsider bias:For instance, on the Cultural Alignment Gap (CAG) metric, MFA-SA reduces bias in Llama model by 89.70 % and MFA-HA mitigates bias in Qwen by 82.54%.These findings showcase the effectiveness of agent-based methods as a promising direction for mitigating biases in generative LLMs.
%R 10.18653/v1/2026.acl-long.1094
%U https://aclanthology.org/2026.acl-long.1094/
%U https://doi.org/10.18653/v1/2026.acl-long.1094
%P 23864-23883
Markdown (Informal)
[InsideOut: Measuring and Mitigating Insider–Outsider Bias in Interview Script Generation](https://aclanthology.org/2026.acl-long.1094/) (Wan et al., ACL 2026)
ACL