@inproceedings{chen-etal-2024-autoprm,
title = "{A}uto{PRM}: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition",
author = "Chen, Zhaorun and
Zhao, Zhuokai and
Zhu, Zhihong and
Zhang, Ruiqi and
Li, Xiang and
Raj, Bhiksha and
Yao, Huaxiu",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.73",
doi = "10.18653/v1/2024.naacl-long.73",
pages = "1346--1362",
abstract = "Recent advancements in large language models (LLMs) have shown promise in multi-step reasoning tasks, yet their reliance on extensive manual labeling to provide procedural feedback remains a significant impediment. To address this challenge, in this paper, we propose a novel self-supervised framework **AutoPRM** that efficiently enhances the fine-tuning of LLMs for intricate reasoning challenges. Specifically, **AutoPRM** first decomposes complex problems into more manageable subquestions with a controllable granularity switch, then sequentially apply reinforcement learning to iteratively improve the subquestion solver. Additionally, we propose context-guided decoding to avoid reward tampering and guide the subquestion solver towards the solution of the holistic problem. Extensive experiments show that **AutoPRM** significantly improves performance on mathematical and commonsense reasoning tasks over SOTA. More encouragingly, **AutoPRM** can be easily integrated with other orthogonal reasoning pipelines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2024-autoprm">
<titleInfo>
<title>AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhaorun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuokai</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhihong</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruiqi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bhiksha</namePart>
<namePart type="family">Raj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huaxiu</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advancements in large language models (LLMs) have shown promise in multi-step reasoning tasks, yet their reliance on extensive manual labeling to provide procedural feedback remains a significant impediment. To address this challenge, in this paper, we propose a novel self-supervised framework **AutoPRM** that efficiently enhances the fine-tuning of LLMs for intricate reasoning challenges. Specifically, **AutoPRM** first decomposes complex problems into more manageable subquestions with a controllable granularity switch, then sequentially apply reinforcement learning to iteratively improve the subquestion solver. Additionally, we propose context-guided decoding to avoid reward tampering and guide the subquestion solver towards the solution of the holistic problem. Extensive experiments show that **AutoPRM** significantly improves performance on mathematical and commonsense reasoning tasks over SOTA. More encouragingly, **AutoPRM** can be easily integrated with other orthogonal reasoning pipelines.</abstract>
<identifier type="citekey">chen-etal-2024-autoprm</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-long.73</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.73</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>1346</start>
<end>1362</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition
%A Chen, Zhaorun
%A Zhao, Zhuokai
%A Zhu, Zhihong
%A Zhang, Ruiqi
%A Li, Xiang
%A Raj, Bhiksha
%A Yao, Huaxiu
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F chen-etal-2024-autoprm
%X Recent advancements in large language models (LLMs) have shown promise in multi-step reasoning tasks, yet their reliance on extensive manual labeling to provide procedural feedback remains a significant impediment. To address this challenge, in this paper, we propose a novel self-supervised framework **AutoPRM** that efficiently enhances the fine-tuning of LLMs for intricate reasoning challenges. Specifically, **AutoPRM** first decomposes complex problems into more manageable subquestions with a controllable granularity switch, then sequentially apply reinforcement learning to iteratively improve the subquestion solver. Additionally, we propose context-guided decoding to avoid reward tampering and guide the subquestion solver towards the solution of the holistic problem. Extensive experiments show that **AutoPRM** significantly improves performance on mathematical and commonsense reasoning tasks over SOTA. More encouragingly, **AutoPRM** can be easily integrated with other orthogonal reasoning pipelines.
%R 10.18653/v1/2024.naacl-long.73
%U https://aclanthology.org/2024.naacl-long.73
%U https://doi.org/10.18653/v1/2024.naacl-long.73
%P 1346-1362
Markdown (Informal)
[AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition](https://aclanthology.org/2024.naacl-long.73) (Chen et al., NAACL 2024)
ACL