@inproceedings{xu-etal-2024-llmrefine,
title = "{LLMR}efine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback",
author = "Xu, Wenda and
Deutsch, Daniel and
Finkelstein, Mara and
Juraska, Juraj and
Zhang, Biao and
Liu, Zhongtao and
Wang, William Yang and
Li, Lei and
Freitag, Markus",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.92",
pages = "1429--1445",
abstract = "Recent large language models (LLM) areleveraging human feedback to improve theirgeneration quality. However, human feedbackis costly to obtain, especially during inference.In this work, we propose LLMRefine, aninference time optimization method to refineLLM{'}s output. The core idea is to usea learned fine-grained feedback model topinpoint defects and guide LLM to refinethem iteratively. Using original LLM as aproposal of edits, LLMRefine searches fordefect-less text via simulated annealing, tradingoff the exploration and exploitation. Weconduct experiments on three text generationtasks, including machine translation, long-form question answering (QA), and topicalsummarization. LLMRefine consistentlyoutperforms all baseline approaches, achievingimprovements up to 1.7 MetricX points ontranslation tasks, 8.1 ROUGE-L on ASQA, 2.2ROUGE-L on topical summarization.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2024-llmrefine">
<titleInfo>
<title>LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenda</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Deutsch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mara</namePart>
<namePart type="family">Finkelstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juraj</namePart>
<namePart type="family">Juraska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongtao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="given">Yang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Freitag</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>Findings of the Association for Computational Linguistics: NAACL 2024</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 large language models (LLM) areleveraging human feedback to improve theirgeneration quality. However, human feedbackis costly to obtain, especially during inference.In this work, we propose LLMRefine, aninference time optimization method to refineLLM’s output. The core idea is to usea learned fine-grained feedback model topinpoint defects and guide LLM to refinethem iteratively. Using original LLM as aproposal of edits, LLMRefine searches fordefect-less text via simulated annealing, tradingoff the exploration and exploitation. Weconduct experiments on three text generationtasks, including machine translation, long-form question answering (QA), and topicalsummarization. LLMRefine consistentlyoutperforms all baseline approaches, achievingimprovements up to 1.7 MetricX points ontranslation tasks, 8.1 ROUGE-L on ASQA, 2.2ROUGE-L on topical summarization.</abstract>
<identifier type="citekey">xu-etal-2024-llmrefine</identifier>
<location>
<url>https://aclanthology.org/2024.findings-naacl.92</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>1429</start>
<end>1445</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback
%A Xu, Wenda
%A Deutsch, Daniel
%A Finkelstein, Mara
%A Juraska, Juraj
%A Zhang, Biao
%A Liu, Zhongtao
%A Wang, William Yang
%A Li, Lei
%A Freitag, Markus
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F xu-etal-2024-llmrefine
%X Recent large language models (LLM) areleveraging human feedback to improve theirgeneration quality. However, human feedbackis costly to obtain, especially during inference.In this work, we propose LLMRefine, aninference time optimization method to refineLLM’s output. The core idea is to usea learned fine-grained feedback model topinpoint defects and guide LLM to refinethem iteratively. Using original LLM as aproposal of edits, LLMRefine searches fordefect-less text via simulated annealing, tradingoff the exploration and exploitation. Weconduct experiments on three text generationtasks, including machine translation, long-form question answering (QA), and topicalsummarization. LLMRefine consistentlyoutperforms all baseline approaches, achievingimprovements up to 1.7 MetricX points ontranslation tasks, 8.1 ROUGE-L on ASQA, 2.2ROUGE-L on topical summarization.
%U https://aclanthology.org/2024.findings-naacl.92
%P 1429-1445
Markdown (Informal)
[LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback](https://aclanthology.org/2024.findings-naacl.92) (Xu et al., Findings 2024)
ACL
- Wenda Xu, Daniel Deutsch, Mara Finkelstein, Juraj Juraska, Biao Zhang, Zhongtao Liu, William Yang Wang, Lei Li, and Markus Freitag. 2024. LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 1429–1445, Mexico City, Mexico. Association for Computational Linguistics.