@inproceedings{sprueill-etal-2023-monte,
title = "{M}onte {C}arlo Thought Search: Large Language Model Querying for Complex Scientific Reasoning in Catalyst Design",
author = "Sprueill, Henry and
Edwards, Carl and
Olarte, Mariefel and
Sanyal, Udishnu and
Ji, Heng and
Choudhury, Sutanay",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.560",
doi = "10.18653/v1/2023.findings-emnlp.560",
pages = "8348--8365",
abstract = "Discovering novel catalysts requires complex reasoning involving multiple chemical properties and resultant trade-offs, leading to a combinatorial growth in the search space. While large language models (LLM) have demonstrated novel capabilities for chemistry through complex instruction following capabilities and high quality reasoning, a goal-driven combinatorial search using LLMs has not been explored in detail. In this work, we present a Monte Carlo Tree Search-based approach that improves beyond state-of-the-art chain-of-thought prompting variants to augment scientific reasoning. We introduce two new reasoning datasets: 1) a curation of computational chemistry simulations, and 2) diverse questions written by catalysis researchers for reasoning about novel chemical conversion processes. We improve over the best baseline by 25.8{\%} and find that our approach can augment scientist{'}s reasoning and discovery process with novel insights.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sprueill-etal-2023-monte">
<titleInfo>
<title>Monte Carlo Thought Search: Large Language Model Querying for Complex Scientific Reasoning in Catalyst Design</title>
</titleInfo>
<name type="personal">
<namePart type="given">Henry</namePart>
<namePart type="family">Sprueill</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carl</namePart>
<namePart type="family">Edwards</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariefel</namePart>
<namePart type="family">Olarte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Udishnu</namePart>
<namePart type="family">Sanyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sutanay</namePart>
<namePart type="family">Choudhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Discovering novel catalysts requires complex reasoning involving multiple chemical properties and resultant trade-offs, leading to a combinatorial growth in the search space. While large language models (LLM) have demonstrated novel capabilities for chemistry through complex instruction following capabilities and high quality reasoning, a goal-driven combinatorial search using LLMs has not been explored in detail. In this work, we present a Monte Carlo Tree Search-based approach that improves beyond state-of-the-art chain-of-thought prompting variants to augment scientific reasoning. We introduce two new reasoning datasets: 1) a curation of computational chemistry simulations, and 2) diverse questions written by catalysis researchers for reasoning about novel chemical conversion processes. We improve over the best baseline by 25.8% and find that our approach can augment scientist’s reasoning and discovery process with novel insights.</abstract>
<identifier type="citekey">sprueill-etal-2023-monte</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.560</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.560</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>8348</start>
<end>8365</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Monte Carlo Thought Search: Large Language Model Querying for Complex Scientific Reasoning in Catalyst Design
%A Sprueill, Henry
%A Edwards, Carl
%A Olarte, Mariefel
%A Sanyal, Udishnu
%A Ji, Heng
%A Choudhury, Sutanay
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F sprueill-etal-2023-monte
%X Discovering novel catalysts requires complex reasoning involving multiple chemical properties and resultant trade-offs, leading to a combinatorial growth in the search space. While large language models (LLM) have demonstrated novel capabilities for chemistry through complex instruction following capabilities and high quality reasoning, a goal-driven combinatorial search using LLMs has not been explored in detail. In this work, we present a Monte Carlo Tree Search-based approach that improves beyond state-of-the-art chain-of-thought prompting variants to augment scientific reasoning. We introduce two new reasoning datasets: 1) a curation of computational chemistry simulations, and 2) diverse questions written by catalysis researchers for reasoning about novel chemical conversion processes. We improve over the best baseline by 25.8% and find that our approach can augment scientist’s reasoning and discovery process with novel insights.
%R 10.18653/v1/2023.findings-emnlp.560
%U https://aclanthology.org/2023.findings-emnlp.560
%U https://doi.org/10.18653/v1/2023.findings-emnlp.560
%P 8348-8365
Markdown (Informal)
[Monte Carlo Thought Search: Large Language Model Querying for Complex Scientific Reasoning in Catalyst Design](https://aclanthology.org/2023.findings-emnlp.560) (Sprueill et al., Findings 2023)
ACL