@inproceedings{arakelyan-etal-2025-flare,
title = "{FLARE}: Faithful Logic-Aided Reasoning and Exploration",
author = "Arakelyan, Erik and
Minervini, Pasquale and
Lewis, Patrick and
Verga, Pat and
Augenstein, Isabelle",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1193/",
doi = "10.18653/v1/2025.emnlp-main.1193",
pages = "23385--23403",
ISBN = "979-8-89176-332-6",
abstract = "Modern Question Answering (QA) and Reasoning approaches with Large Language Models (LLMs) commonly use Chain-of-Thought (CoT) prompting but struggle with generating outputs faithful to their intermediate reasoning chains. While neuro-symbolic methods like Faithful CoT (F-CoT) offer higher faithfulness through external solvers, they require code-specialized models and struggle with ambiguous tasks.We introduce $\textbf{F}$aithful $\textbf{L}$ogic-$\textbf{A}$ided $\textbf{R}$easoning and $\textbf{E}$xploration ($\textbf{FLARE}$), which uses LLMs to plan solutions, formalize queries into logic programs, and simulate code execution through multi-hop search without external solvers. Our method achieves SOTA results on $\mathbf{7}$ out of $\mathbf{9}$ diverse reasoning benchmarks and 3 out of 3 logic inference benchmarks while enabling measurement of reasoning faithfulness. We demonstrate that model faithfulness correlates with performance and that successful reasoning traces show an 18.1{\%} increase in unique emergent facts, 8.6{\%} higher overlap between code-defined and execution-trace relations, and 3.6{\%} reduction in unused relations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arakelyan-etal-2025-flare">
<titleInfo>
<title>FLARE: Faithful Logic-Aided Reasoning and Exploration</title>
</titleInfo>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Arakelyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pasquale</namePart>
<namePart type="family">Minervini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pat</namePart>
<namePart type="family">Verga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Modern Question Answering (QA) and Reasoning approaches with Large Language Models (LLMs) commonly use Chain-of-Thought (CoT) prompting but struggle with generating outputs faithful to their intermediate reasoning chains. While neuro-symbolic methods like Faithful CoT (F-CoT) offer higher faithfulness through external solvers, they require code-specialized models and struggle with ambiguous tasks.We introduce Faithful Logic-Aided Reasoning and Exploration (FLARE), which uses LLMs to plan solutions, formalize queries into logic programs, and simulate code execution through multi-hop search without external solvers. Our method achieves SOTA results on \mathbf7 out of \mathbf9 diverse reasoning benchmarks and 3 out of 3 logic inference benchmarks while enabling measurement of reasoning faithfulness. We demonstrate that model faithfulness correlates with performance and that successful reasoning traces show an 18.1% increase in unique emergent facts, 8.6% higher overlap between code-defined and execution-trace relations, and 3.6% reduction in unused relations.</abstract>
<identifier type="citekey">arakelyan-etal-2025-flare</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.1193</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1193/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>23385</start>
<end>23403</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FLARE: Faithful Logic-Aided Reasoning and Exploration
%A Arakelyan, Erik
%A Minervini, Pasquale
%A Lewis, Patrick
%A Verga, Pat
%A Augenstein, Isabelle
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F arakelyan-etal-2025-flare
%X Modern Question Answering (QA) and Reasoning approaches with Large Language Models (LLMs) commonly use Chain-of-Thought (CoT) prompting but struggle with generating outputs faithful to their intermediate reasoning chains. While neuro-symbolic methods like Faithful CoT (F-CoT) offer higher faithfulness through external solvers, they require code-specialized models and struggle with ambiguous tasks.We introduce Faithful Logic-Aided Reasoning and Exploration (FLARE), which uses LLMs to plan solutions, formalize queries into logic programs, and simulate code execution through multi-hop search without external solvers. Our method achieves SOTA results on \mathbf7 out of \mathbf9 diverse reasoning benchmarks and 3 out of 3 logic inference benchmarks while enabling measurement of reasoning faithfulness. We demonstrate that model faithfulness correlates with performance and that successful reasoning traces show an 18.1% increase in unique emergent facts, 8.6% higher overlap between code-defined and execution-trace relations, and 3.6% reduction in unused relations.
%R 10.18653/v1/2025.emnlp-main.1193
%U https://aclanthology.org/2025.emnlp-main.1193/
%U https://doi.org/10.18653/v1/2025.emnlp-main.1193
%P 23385-23403
Markdown (Informal)
[FLARE: Faithful Logic-Aided Reasoning and Exploration](https://aclanthology.org/2025.emnlp-main.1193/) (Arakelyan et al., EMNLP 2025)
ACL
- Erik Arakelyan, Pasquale Minervini, Patrick Lewis, Pat Verga, and Isabelle Augenstein. 2025. FLARE: Faithful Logic-Aided Reasoning and Exploration. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 23385–23403, Suzhou, China. Association for Computational Linguistics.