@inproceedings{nayan-bala-2026-quantization,
title = "Does Quantization Change What Agreement Means? A Paired Audit of Homogeneous {LLM} Panels",
author = "Nayan Bala, Ananto",
editor = {Aziz, Wilker and
Berant, Jonathan and
Eikema, Bryan and
Ilia, Evgenia and
de Marneffe, Marie-Catherine and
Plank, Barbara and
Shelmanov, Artem and
Swayamdipta, Swabha and
Tiedemann, J{\"o}rg and
Vazhentsev, Artem and
V{\'a}zquez, Ra{\'u}l and
Zerva, Chrysoula},
booktitle = "The Proceedings of the Third Workshop on Uncertainty-Aware {NLP}",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.uncertainlp-main.37/",
pages = "618--624",
ISBN = "979-8-89176-486-6",
abstract = "Agreement among repeated large language model (LLM) responses is often used as a confidence signal. We test whether that signal changes after quantization by comparing five-response panels from the same checkpoints at FP16 and 4-bit NF4. We evaluate two open models on 300 TruthfulQA multiple-choice questions and 300 GSM8K problems, matching prompts, sampling settings, and seeds. Under strict parsing, quantization reduces GSM8K panel accuracy by 10.5 percentage points for Qwen2.5-3B and 6.3 for Phi-3.5-mini. The probability that all five responses are wrong rises by 9.0 and 5.0 points. Agreement also becomes less useful for selecting reliable answers, but all-wrong panels do not consistently become more likely to give one identical answer. Relaxed parsing preserves the selective-reliability result for both models, although Phi{'}s panel-accuracy and all-wrong differences become inconclusive. On TruthfulQA, Phi degrades while Qwen is largely stable. Quantization can therefore reduce panel reliability without consistently pushing all members toward the same wrong answer."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nayan-bala-2026-quantization">
<titleInfo>
<title>Does Quantization Change What Agreement Means? A Paired Audit of Homogeneous LLM Panels</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ananto</namePart>
<namePart type="family">Nayan Bala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>The Proceedings of the Third Workshop on Uncertainty-Aware NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wilker</namePart>
<namePart type="family">Aziz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Berant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="family">Eikema</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evgenia</namePart>
<namePart type="family">Ilia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Shelmanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Vazhentsev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raúl</namePart>
<namePart type="family">Vázquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chrysoula</namePart>
<namePart type="family">Zerva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-486-6</identifier>
</relatedItem>
<abstract>Agreement among repeated large language model (LLM) responses is often used as a confidence signal. We test whether that signal changes after quantization by comparing five-response panels from the same checkpoints at FP16 and 4-bit NF4. We evaluate two open models on 300 TruthfulQA multiple-choice questions and 300 GSM8K problems, matching prompts, sampling settings, and seeds. Under strict parsing, quantization reduces GSM8K panel accuracy by 10.5 percentage points for Qwen2.5-3B and 6.3 for Phi-3.5-mini. The probability that all five responses are wrong rises by 9.0 and 5.0 points. Agreement also becomes less useful for selecting reliable answers, but all-wrong panels do not consistently become more likely to give one identical answer. Relaxed parsing preserves the selective-reliability result for both models, although Phi’s panel-accuracy and all-wrong differences become inconclusive. On TruthfulQA, Phi degrades while Qwen is largely stable. Quantization can therefore reduce panel reliability without consistently pushing all members toward the same wrong answer.</abstract>
<identifier type="citekey">nayan-bala-2026-quantization</identifier>
<location>
<url>https://aclanthology.org/2026.uncertainlp-main.37/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>618</start>
<end>624</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Does Quantization Change What Agreement Means? A Paired Audit of Homogeneous LLM Panels
%A Nayan Bala, Ananto
%Y Aziz, Wilker
%Y Berant, Jonathan
%Y Eikema, Bryan
%Y Ilia, Evgenia
%Y de Marneffe, Marie-Catherine
%Y Plank, Barbara
%Y Shelmanov, Artem
%Y Swayamdipta, Swabha
%Y Tiedemann, Jörg
%Y Vazhentsev, Artem
%Y Vázquez, Raúl
%Y Zerva, Chrysoula
%S The Proceedings of the Third Workshop on Uncertainty-Aware NLP
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-486-6
%F nayan-bala-2026-quantization
%X Agreement among repeated large language model (LLM) responses is often used as a confidence signal. We test whether that signal changes after quantization by comparing five-response panels from the same checkpoints at FP16 and 4-bit NF4. We evaluate two open models on 300 TruthfulQA multiple-choice questions and 300 GSM8K problems, matching prompts, sampling settings, and seeds. Under strict parsing, quantization reduces GSM8K panel accuracy by 10.5 percentage points for Qwen2.5-3B and 6.3 for Phi-3.5-mini. The probability that all five responses are wrong rises by 9.0 and 5.0 points. Agreement also becomes less useful for selecting reliable answers, but all-wrong panels do not consistently become more likely to give one identical answer. Relaxed parsing preserves the selective-reliability result for both models, although Phi’s panel-accuracy and all-wrong differences become inconclusive. On TruthfulQA, Phi degrades while Qwen is largely stable. Quantization can therefore reduce panel reliability without consistently pushing all members toward the same wrong answer.
%U https://aclanthology.org/2026.uncertainlp-main.37/
%P 618-624
Markdown (Informal)
[Does Quantization Change What Agreement Means? A Paired Audit of Homogeneous LLM Panels](https://aclanthology.org/2026.uncertainlp-main.37/) (Nayan Bala, UncertaiNLP 2026)
ACL