@inproceedings{zhang-etal-2026-prompting,
title = "Prompting the Unknown: Understanding Response Uncertainty in Large Language Models",
author = "Zhang, Ze Yu and
Verma, Arun and
Doshi-Velez, Finale and
Low, Bryan Kian Hsiang",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1548/",
pages = "30956--30984",
ISBN = "979-8-89176-395-1",
abstract = "Large language models (LLMs) are widely used in decision-making across diverse domains. Ensuring the generation of safe and reliable responses is critical for the effective deployment of LLM-based applications, particularly in high-stakes domains such as healthcare and finance. Most of these applications typically use carefully crafted prompts to guide response generation; however, the relationship between prompts and the reliability of LLM-generated responses is not yet fully understood. To address this gap, we propose a novel prompt-response concept model that explains the relationship between the amount of task-relevant information (informativeness) provided in the prompt and the LLM-generated response uncertainty by identifying four sources of response uncertainty: prompt underspecification, model quality, task variability, and semantic redundancy. We prove that response uncertainty decreases as prompt informativeness or model quality increases, mirroring the behavior of epistemic uncertainty in probabilistic models. Our experimental results on real-world datasets further validate our proposed model and corroborate the theoretical results."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-prompting">
<titleInfo>
<title>Prompting the Unknown: Understanding Response Uncertainty in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ze</namePart>
<namePart type="given">Yu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arun</namePart>
<namePart type="family">Verma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Finale</namePart>
<namePart type="family">Doshi-Velez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="given">Kian</namePart>
<namePart type="given">Hsiang</namePart>
<namePart type="family">Low</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>Findings of the Association for Computational Linguistics: ACL 2026</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">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Large language models (LLMs) are widely used in decision-making across diverse domains. Ensuring the generation of safe and reliable responses is critical for the effective deployment of LLM-based applications, particularly in high-stakes domains such as healthcare and finance. Most of these applications typically use carefully crafted prompts to guide response generation; however, the relationship between prompts and the reliability of LLM-generated responses is not yet fully understood. To address this gap, we propose a novel prompt-response concept model that explains the relationship between the amount of task-relevant information (informativeness) provided in the prompt and the LLM-generated response uncertainty by identifying four sources of response uncertainty: prompt underspecification, model quality, task variability, and semantic redundancy. We prove that response uncertainty decreases as prompt informativeness or model quality increases, mirroring the behavior of epistemic uncertainty in probabilistic models. Our experimental results on real-world datasets further validate our proposed model and corroborate the theoretical results.</abstract>
<identifier type="citekey">zhang-etal-2026-prompting</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1548/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>30956</start>
<end>30984</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Prompting the Unknown: Understanding Response Uncertainty in Large Language Models
%A Zhang, Ze Yu
%A Verma, Arun
%A Doshi-Velez, Finale
%A Low, Bryan Kian Hsiang
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F zhang-etal-2026-prompting
%X Large language models (LLMs) are widely used in decision-making across diverse domains. Ensuring the generation of safe and reliable responses is critical for the effective deployment of LLM-based applications, particularly in high-stakes domains such as healthcare and finance. Most of these applications typically use carefully crafted prompts to guide response generation; however, the relationship between prompts and the reliability of LLM-generated responses is not yet fully understood. To address this gap, we propose a novel prompt-response concept model that explains the relationship between the amount of task-relevant information (informativeness) provided in the prompt and the LLM-generated response uncertainty by identifying four sources of response uncertainty: prompt underspecification, model quality, task variability, and semantic redundancy. We prove that response uncertainty decreases as prompt informativeness or model quality increases, mirroring the behavior of epistemic uncertainty in probabilistic models. Our experimental results on real-world datasets further validate our proposed model and corroborate the theoretical results.
%U https://aclanthology.org/2026.findings-acl.1548/
%P 30956-30984
Markdown (Informal)
[Prompting the Unknown: Understanding Response Uncertainty in Large Language Models](https://aclanthology.org/2026.findings-acl.1548/) (Zhang et al., Findings 2026)
ACL