@inproceedings{bharati-etal-2026-frost,
title = "{FROST}: Factual Reasoning via Optimized Stochastic Trajectories in Large Language Models during Inference",
author = "Bharati, Soumedhik and
Shabbir, Ebad and
Gao, Jiechao",
editor = "Li, Yunyao and
Rehm, Georg and
Tu, Mei",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-industry.77/",
pages = "1105--1113",
ISBN = "979-8-89176-394-4",
abstract = "Large language models face a trade-off between factual consistency and reasoningdiversity: deterministic decoding prioritizes reliability but may miss alternativesolution paths, while high-temperature sampling increases exploration at the costof accuracy. We present FROST (Factual Reasoning via Optimized StochasticTrajectories), an inference-time framework that balances exploration andexploitation without additional training or context augmentation. FROST combinesdeterministic inference from a large model with targeted stochastic sampling froma smaller model, selecting outputs via multi-criteria validation over coherence,factual grounding, and semantic novelty. Across HotpotQA, CommonsenseQA, andMMLU, FROST achieves 2{--}5 percentage point improvements over standard chain-of-thoughtprompting and reduces unsupported outputs by 40{\%} relative to Standard CoT. Comparedto Self-Consistency ensembles, FROST delivers comparable accuracy at 28{\%} lowerinference cost through strategic delegation to smaller models. On an adversarialsubset with unanswerable queries, FROST abstains on 34{\%} of cases versus 8{\%} forstandard chain-of-thought, reducing false positives by 45{\%}. Task-stratifiedevaluation shows that exploration benefits scale with problem ambiguity.Generalization to mathematical reasoning, code generation, and multimodal domainsremains future work."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bharati-etal-2026-frost">
<titleInfo>
<title>FROST: Factual Reasoning via Optimized Stochastic Trajectories in Large Language Models during Inference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Soumedhik</namePart>
<namePart type="family">Bharati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ebad</namePart>
<namePart type="family">Shabbir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiechao</namePart>
<namePart type="family">Gao</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>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Tu</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, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-394-4</identifier>
</relatedItem>
<abstract>Large language models face a trade-off between factual consistency and reasoningdiversity: deterministic decoding prioritizes reliability but may miss alternativesolution paths, while high-temperature sampling increases exploration at the costof accuracy. We present FROST (Factual Reasoning via Optimized StochasticTrajectories), an inference-time framework that balances exploration andexploitation without additional training or context augmentation. FROST combinesdeterministic inference from a large model with targeted stochastic sampling froma smaller model, selecting outputs via multi-criteria validation over coherence,factual grounding, and semantic novelty. Across HotpotQA, CommonsenseQA, andMMLU, FROST achieves 2–5 percentage point improvements over standard chain-of-thoughtprompting and reduces unsupported outputs by 40% relative to Standard CoT. Comparedto Self-Consistency ensembles, FROST delivers comparable accuracy at 28% lowerinference cost through strategic delegation to smaller models. On an adversarialsubset with unanswerable queries, FROST abstains on 34% of cases versus 8% forstandard chain-of-thought, reducing false positives by 45%. Task-stratifiedevaluation shows that exploration benefits scale with problem ambiguity.Generalization to mathematical reasoning, code generation, and multimodal domainsremains future work.</abstract>
<identifier type="citekey">bharati-etal-2026-frost</identifier>
<location>
<url>https://aclanthology.org/2026.acl-industry.77/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1105</start>
<end>1113</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FROST: Factual Reasoning via Optimized Stochastic Trajectories in Large Language Models during Inference
%A Bharati, Soumedhik
%A Shabbir, Ebad
%A Gao, Jiechao
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F bharati-etal-2026-frost
%X Large language models face a trade-off between factual consistency and reasoningdiversity: deterministic decoding prioritizes reliability but may miss alternativesolution paths, while high-temperature sampling increases exploration at the costof accuracy. We present FROST (Factual Reasoning via Optimized StochasticTrajectories), an inference-time framework that balances exploration andexploitation without additional training or context augmentation. FROST combinesdeterministic inference from a large model with targeted stochastic sampling froma smaller model, selecting outputs via multi-criteria validation over coherence,factual grounding, and semantic novelty. Across HotpotQA, CommonsenseQA, andMMLU, FROST achieves 2–5 percentage point improvements over standard chain-of-thoughtprompting and reduces unsupported outputs by 40% relative to Standard CoT. Comparedto Self-Consistency ensembles, FROST delivers comparable accuracy at 28% lowerinference cost through strategic delegation to smaller models. On an adversarialsubset with unanswerable queries, FROST abstains on 34% of cases versus 8% forstandard chain-of-thought, reducing false positives by 45%. Task-stratifiedevaluation shows that exploration benefits scale with problem ambiguity.Generalization to mathematical reasoning, code generation, and multimodal domainsremains future work.
%U https://aclanthology.org/2026.acl-industry.77/
%P 1105-1113
Markdown (Informal)
[FROST: Factual Reasoning via Optimized Stochastic Trajectories in Large Language Models during Inference](https://aclanthology.org/2026.acl-industry.77/) (Bharati et al., ACL 2026)
ACL