@inproceedings{byun-choi-2025-gen,
title = "\textit{ {D}-{GEN}}: Automatic Distractor Generation and Evaluation for Reliable Assessment of Generative Models",
author = "Byun, Grace and
Choi, Jinho D.",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.174/",
doi = "10.18653/v1/2025.findings-acl.174",
pages = "3316--3349",
ISBN = "979-8-89176-256-5",
abstract = "Evaluating generative models with open-ended generation is challenging due to inconsistencies in response formats. Multiple-choice (MC) evaluation mitigates this issue, but generating high-quality distractors is time-consuming and labor-intensive. We introduce \textit{D-GEN}, the first open-source distractor generator model that transforms open-ended data into an MC format. To evaluate distractor quality, we propose two novel methods: 1) ranking alignment, ensuring generated distractors retain the discriminatory power of ground-truth distractors, and 2) entropy analysis, comparing model confidence distributions. Our results show that \textit{D-GEN} preserves ranking consistency (Spearman{'}s $\rho$ 0.99, Kendall{'}s $\tau$ 0.94) and closely matches the entropy distribution of ground-truth distractors. Human evaluation further confirms the fluency, coherence, distractiveness, and incorrectness. Our work advances robust and efficient distractor generation with automated evaluation, setting a new standard for MC evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="byun-choi-2025-gen">
<titleInfo>
<title> D-GEN: Automatic Distractor Generation and Evaluation for Reliable Assessment of Generative Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Grace</namePart>
<namePart type="family">Byun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinho</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Evaluating generative models with open-ended generation is challenging due to inconsistencies in response formats. Multiple-choice (MC) evaluation mitigates this issue, but generating high-quality distractors is time-consuming and labor-intensive. We introduce D-GEN, the first open-source distractor generator model that transforms open-ended data into an MC format. To evaluate distractor quality, we propose two novel methods: 1) ranking alignment, ensuring generated distractors retain the discriminatory power of ground-truth distractors, and 2) entropy analysis, comparing model confidence distributions. Our results show that D-GEN preserves ranking consistency (Spearman’s ρ 0.99, Kendall’s τ 0.94) and closely matches the entropy distribution of ground-truth distractors. Human evaluation further confirms the fluency, coherence, distractiveness, and incorrectness. Our work advances robust and efficient distractor generation with automated evaluation, setting a new standard for MC evaluation.</abstract>
<identifier type="citekey">byun-choi-2025-gen</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.174</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.174/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>3316</start>
<end>3349</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T D-GEN: Automatic Distractor Generation and Evaluation for Reliable Assessment of Generative Models
%A Byun, Grace
%A Choi, Jinho D.
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F byun-choi-2025-gen
%X Evaluating generative models with open-ended generation is challenging due to inconsistencies in response formats. Multiple-choice (MC) evaluation mitigates this issue, but generating high-quality distractors is time-consuming and labor-intensive. We introduce D-GEN, the first open-source distractor generator model that transforms open-ended data into an MC format. To evaluate distractor quality, we propose two novel methods: 1) ranking alignment, ensuring generated distractors retain the discriminatory power of ground-truth distractors, and 2) entropy analysis, comparing model confidence distributions. Our results show that D-GEN preserves ranking consistency (Spearman’s ρ 0.99, Kendall’s τ 0.94) and closely matches the entropy distribution of ground-truth distractors. Human evaluation further confirms the fluency, coherence, distractiveness, and incorrectness. Our work advances robust and efficient distractor generation with automated evaluation, setting a new standard for MC evaluation.
%R 10.18653/v1/2025.findings-acl.174
%U https://aclanthology.org/2025.findings-acl.174/
%U https://doi.org/10.18653/v1/2025.findings-acl.174
%P 3316-3349
Markdown (Informal)
[D-GEN: Automatic Distractor Generation and Evaluation for Reliable Assessment of Generative Models](https://aclanthology.org/2025.findings-acl.174/) (Byun & Choi, Findings 2025)
ACL