@inproceedings{sun-saparov-2026-language,
title = "Do Language Models Follow Occam{'}s Razor? An Evaluation of Parsimony in Inductive and Abductive Reasoning",
author = "Sun, Yunxin and
Saparov, Abulhair",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2439/",
pages = "55345--55366",
ISBN = "979-8-89176-459-0",
abstract = "Non-deductive reasoning, encompassing inductive and abductive reasoning, is essential in addressing complex real-world questions. One key feature of inductive and abductive reasoning is that there are many valid hypotheses; the simplest ones (those that adhere to Occam{'}s razor) are often most useful. However, this aspect is ignored in recent work that evaluates the non-deductive reasoning capabilities of large language models (LLMs). This work fills this gap, focusing on understanding whether the inductive and abductive reasoning capabilities of LLMs adhere to Occam{'}s razor, while also examining the correctness of their reasoning. To accomplish this goal, we introduce a framework to synthetically generate reasoning questions that *(a)* require inductive reasoning and abductive reasoning simultaneously; *(b)* is readily extended to produce any abductive/inductive reasoning question expressible in first-order logic. The task for the intelligent agent is to produce hypotheses to *explain* observations under a given world model. We also propose a new automated metric to assess whether hypotheses quantitatively adhere to Occam{'}s razor; those hypotheses that are correct and simplest are considered *high-quality*. Our findings on state-of-the-art LLMs suggest that LLMs can perform inductive and abductive reasoning in simple scenarios, but struggle with complex world models and with producing *high-quality* hypotheses, even with popular reasoning-enhancing techniques such as in-context learning and RLVR."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-saparov-2026-language">
<titleInfo>
<title>Do Language Models Follow Occam’s Razor? An Evaluation of Parsimony in Inductive and Abductive Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunxin</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abulhair</namePart>
<namePart type="family">Saparov</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Non-deductive reasoning, encompassing inductive and abductive reasoning, is essential in addressing complex real-world questions. One key feature of inductive and abductive reasoning is that there are many valid hypotheses; the simplest ones (those that adhere to Occam’s razor) are often most useful. However, this aspect is ignored in recent work that evaluates the non-deductive reasoning capabilities of large language models (LLMs). This work fills this gap, focusing on understanding whether the inductive and abductive reasoning capabilities of LLMs adhere to Occam’s razor, while also examining the correctness of their reasoning. To accomplish this goal, we introduce a framework to synthetically generate reasoning questions that *(a)* require inductive reasoning and abductive reasoning simultaneously; *(b)* is readily extended to produce any abductive/inductive reasoning question expressible in first-order logic. The task for the intelligent agent is to produce hypotheses to *explain* observations under a given world model. We also propose a new automated metric to assess whether hypotheses quantitatively adhere to Occam’s razor; those hypotheses that are correct and simplest are considered *high-quality*. Our findings on state-of-the-art LLMs suggest that LLMs can perform inductive and abductive reasoning in simple scenarios, but struggle with complex world models and with producing *high-quality* hypotheses, even with popular reasoning-enhancing techniques such as in-context learning and RLVR.</abstract>
<identifier type="citekey">sun-saparov-2026-language</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2439/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>55345</start>
<end>55366</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do Language Models Follow Occam’s Razor? An Evaluation of Parsimony in Inductive and Abductive Reasoning
%A Sun, Yunxin
%A Saparov, Abulhair
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F sun-saparov-2026-language
%X Non-deductive reasoning, encompassing inductive and abductive reasoning, is essential in addressing complex real-world questions. One key feature of inductive and abductive reasoning is that there are many valid hypotheses; the simplest ones (those that adhere to Occam’s razor) are often most useful. However, this aspect is ignored in recent work that evaluates the non-deductive reasoning capabilities of large language models (LLMs). This work fills this gap, focusing on understanding whether the inductive and abductive reasoning capabilities of LLMs adhere to Occam’s razor, while also examining the correctness of their reasoning. To accomplish this goal, we introduce a framework to synthetically generate reasoning questions that *(a)* require inductive reasoning and abductive reasoning simultaneously; *(b)* is readily extended to produce any abductive/inductive reasoning question expressible in first-order logic. The task for the intelligent agent is to produce hypotheses to *explain* observations under a given world model. We also propose a new automated metric to assess whether hypotheses quantitatively adhere to Occam’s razor; those hypotheses that are correct and simplest are considered *high-quality*. Our findings on state-of-the-art LLMs suggest that LLMs can perform inductive and abductive reasoning in simple scenarios, but struggle with complex world models and with producing *high-quality* hypotheses, even with popular reasoning-enhancing techniques such as in-context learning and RLVR.
%U https://aclanthology.org/2026.emnlp-main.2439/
%P 55345-55366
Markdown (Informal)
[Do Language Models Follow Occam’s Razor? An Evaluation of Parsimony in Inductive and Abductive Reasoning](https://aclanthology.org/2026.emnlp-main.2439/) (Sun & Saparov, EMNLP 2026)
ACL