@inproceedings{abdolmaleki-etal-2026-counter,
title = "Counter-Hypothesis Generation: Towards Evaluating How {LLM}s Reason about Alternatives",
author = "Abdolmaleki, Marzieh and
Maladry, Aaron and
Hoste, Veronique and
Lefever, Els",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.424/",
doi = "10.63317/336pssnozxaw",
pages = "5445--5449",
abstract = "Reasoning about alternatives is a fundamental component of human cognition and argumentation, yet it remains unclear whether large language models (LLMs) can coherently generate and assess them. This paper introduces Counter-Hypothesis Generation (CHG), a novel task for evaluating how LLMs construct plausible hypotheses when contextual information changes. Inspired by open-domain commonsense reasoning, where models infer and compare multiple explanations, CHG bridges commonsense and counterfactual reasoning by requiring models to generate hypotheses that remain logically consistent with modified premises. We present a test set annotated by a human expert and complemented with counter-hypotheses generated by OpenAI-o3 and DeepSeek-r1. Experimental results reveal that even advanced reasoning models exhibit notable limitations in counter-hypothesis generation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abdolmaleki-etal-2026-counter">
<titleInfo>
<title>Counter-Hypothesis Generation: Towards Evaluating How LLMs Reason about Alternatives</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marzieh</namePart>
<namePart type="family">Abdolmaleki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Maladry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Els</namePart>
<namePart type="family">Lefever</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Reasoning about alternatives is a fundamental component of human cognition and argumentation, yet it remains unclear whether large language models (LLMs) can coherently generate and assess them. This paper introduces Counter-Hypothesis Generation (CHG), a novel task for evaluating how LLMs construct plausible hypotheses when contextual information changes. Inspired by open-domain commonsense reasoning, where models infer and compare multiple explanations, CHG bridges commonsense and counterfactual reasoning by requiring models to generate hypotheses that remain logically consistent with modified premises. We present a test set annotated by a human expert and complemented with counter-hypotheses generated by OpenAI-o3 and DeepSeek-r1. Experimental results reveal that even advanced reasoning models exhibit notable limitations in counter-hypothesis generation.</abstract>
<identifier type="citekey">abdolmaleki-etal-2026-counter</identifier>
<identifier type="doi">10.63317/336pssnozxaw</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.424/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>5445</start>
<end>5449</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Counter-Hypothesis Generation: Towards Evaluating How LLMs Reason about Alternatives
%A Abdolmaleki, Marzieh
%A Maladry, Aaron
%A Hoste, Veronique
%A Lefever, Els
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F abdolmaleki-etal-2026-counter
%X Reasoning about alternatives is a fundamental component of human cognition and argumentation, yet it remains unclear whether large language models (LLMs) can coherently generate and assess them. This paper introduces Counter-Hypothesis Generation (CHG), a novel task for evaluating how LLMs construct plausible hypotheses when contextual information changes. Inspired by open-domain commonsense reasoning, where models infer and compare multiple explanations, CHG bridges commonsense and counterfactual reasoning by requiring models to generate hypotheses that remain logically consistent with modified premises. We present a test set annotated by a human expert and complemented with counter-hypotheses generated by OpenAI-o3 and DeepSeek-r1. Experimental results reveal that even advanced reasoning models exhibit notable limitations in counter-hypothesis generation.
%R 10.63317/336pssnozxaw
%U https://aclanthology.org/2026.lrec-1.424/
%U https://doi.org/10.63317/336pssnozxaw
%P 5445-5449
Markdown (Informal)
[Counter-Hypothesis Generation: Towards Evaluating How LLMs Reason about Alternatives](https://aclanthology.org/2026.lrec-1.424/) (Abdolmaleki et al., LREC 2026)
ACL