@inproceedings{kalbaliyev-sirts-2026-refer,
title = "Refer, Infer, or Abstain: Investigating Latent Skill Selection of Large Language Models under Contextual Question Answering Uncertainty",
author = "Kalbaliyev, Emil and
Sirts, Kairit",
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.39/",
pages = "657--671",
ISBN = "979-8-89176-486-6",
abstract = "Contextual question answering (CQA) involves uncertainty regarding the use of available knowledge in forming an answer. In CQA, large language models (LLMs) should decide whether to Refer to explicitly stated information, Infer from contextual evidence using commonsense knowledge, or Abstain when an answer cannot be supported. We investigate whether LLMs implicitly select among these skills under CQA uncertainty. Combining prompting analysis with layer-wise probing, we examine latent skill selection across instruction-tuned LLMs. We find that the models distinguish Refer from Infer more easily than Infer from Abstain. In particular, erroneous abstentions disproportionately occur on inference-based questions, and the Infer{--}Abstain distinction is the least separable in model representations. We further find that models represent contextual knowledge gaps more strongly than contextual knowledge sufficiency. These results characterize the emergence and limitations of latent skill selection in LLMs under CQA uncertainty."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kalbaliyev-sirts-2026-refer">
<titleInfo>
<title>Refer, Infer, or Abstain: Investigating Latent Skill Selection of Large Language Models under Contextual Question Answering Uncertainty</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emil</namePart>
<namePart type="family">Kalbaliyev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kairit</namePart>
<namePart type="family">Sirts</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>Contextual question answering (CQA) involves uncertainty regarding the use of available knowledge in forming an answer. In CQA, large language models (LLMs) should decide whether to Refer to explicitly stated information, Infer from contextual evidence using commonsense knowledge, or Abstain when an answer cannot be supported. We investigate whether LLMs implicitly select among these skills under CQA uncertainty. Combining prompting analysis with layer-wise probing, we examine latent skill selection across instruction-tuned LLMs. We find that the models distinguish Refer from Infer more easily than Infer from Abstain. In particular, erroneous abstentions disproportionately occur on inference-based questions, and the Infer–Abstain distinction is the least separable in model representations. We further find that models represent contextual knowledge gaps more strongly than contextual knowledge sufficiency. These results characterize the emergence and limitations of latent skill selection in LLMs under CQA uncertainty.</abstract>
<identifier type="citekey">kalbaliyev-sirts-2026-refer</identifier>
<location>
<url>https://aclanthology.org/2026.uncertainlp-main.39/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>657</start>
<end>671</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Refer, Infer, or Abstain: Investigating Latent Skill Selection of Large Language Models under Contextual Question Answering Uncertainty
%A Kalbaliyev, Emil
%A Sirts, Kairit
%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 kalbaliyev-sirts-2026-refer
%X Contextual question answering (CQA) involves uncertainty regarding the use of available knowledge in forming an answer. In CQA, large language models (LLMs) should decide whether to Refer to explicitly stated information, Infer from contextual evidence using commonsense knowledge, or Abstain when an answer cannot be supported. We investigate whether LLMs implicitly select among these skills under CQA uncertainty. Combining prompting analysis with layer-wise probing, we examine latent skill selection across instruction-tuned LLMs. We find that the models distinguish Refer from Infer more easily than Infer from Abstain. In particular, erroneous abstentions disproportionately occur on inference-based questions, and the Infer–Abstain distinction is the least separable in model representations. We further find that models represent contextual knowledge gaps more strongly than contextual knowledge sufficiency. These results characterize the emergence and limitations of latent skill selection in LLMs under CQA uncertainty.
%U https://aclanthology.org/2026.uncertainlp-main.39/
%P 657-671
Markdown (Informal)
[Refer, Infer, or Abstain: Investigating Latent Skill Selection of Large Language Models under Contextual Question Answering Uncertainty](https://aclanthology.org/2026.uncertainlp-main.39/) (Kalbaliyev & Sirts, UncertaiNLP 2026)
ACL