@inproceedings{chen-etal-2024-xplainllm,
title = "{X}plain{LLM}: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in {LLM}s",
author = "Chen, Zichen and
Chen, Jianda and
Singh, Ambuj and
Sra, Misha",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.432/",
doi = "10.18653/v1/2024.emnlp-main.432",
pages = "7578--7596",
abstract = "Large Language Models (LLMs) have achieved remarkable success in natural language tasks, yet understanding their reasoning processes remains a significant challenge. We address this by introducing XplainLLM, a dataset accompanying an explanation framework designed to enhance LLM transparency and reliability. Our dataset comprises 24,204 instances where each instance interprets the LLM`s reasoning behavior using knowledge graphs (KGs) and graph attention networks (GAT), and includes explanations of LLMs such as the decoder-only Llama-3 and the encoder-only RoBERTa. XplainLLM also features a framework for generating grounded explanations and the \textit{debugger-scores} for multidimensional quality analysis. Our explanations include \textit{why-choose} and \textit{why-not-choose} components, \textit{reason-elements}, and \textit{debugger-scores} that collectively illuminate the LLM`s reasoning behavior. Our evaluations demonstrate XplainLLM`s potential to reduce hallucinations and improve grounded explanation generation in LLMs. XplainLLM is a resource for researchers and practitioners to build trust and verify the reliability of LLM outputs. Our code and dataset are publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2024-xplainllm">
<titleInfo>
<title>XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zichen</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianda</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ambuj</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Misha</namePart>
<namePart type="family">Sra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) have achieved remarkable success in natural language tasks, yet understanding their reasoning processes remains a significant challenge. We address this by introducing XplainLLM, a dataset accompanying an explanation framework designed to enhance LLM transparency and reliability. Our dataset comprises 24,204 instances where each instance interprets the LLM‘s reasoning behavior using knowledge graphs (KGs) and graph attention networks (GAT), and includes explanations of LLMs such as the decoder-only Llama-3 and the encoder-only RoBERTa. XplainLLM also features a framework for generating grounded explanations and the debugger-scores for multidimensional quality analysis. Our explanations include why-choose and why-not-choose components, reason-elements, and debugger-scores that collectively illuminate the LLM‘s reasoning behavior. Our evaluations demonstrate XplainLLM‘s potential to reduce hallucinations and improve grounded explanation generation in LLMs. XplainLLM is a resource for researchers and practitioners to build trust and verify the reliability of LLM outputs. Our code and dataset are publicly available.</abstract>
<identifier type="citekey">chen-etal-2024-xplainllm</identifier>
<identifier type="doi">10.18653/v1/2024.emnlp-main.432</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.432/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>7578</start>
<end>7596</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs
%A Chen, Zichen
%A Chen, Jianda
%A Singh, Ambuj
%A Sra, Misha
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F chen-etal-2024-xplainllm
%X Large Language Models (LLMs) have achieved remarkable success in natural language tasks, yet understanding their reasoning processes remains a significant challenge. We address this by introducing XplainLLM, a dataset accompanying an explanation framework designed to enhance LLM transparency and reliability. Our dataset comprises 24,204 instances where each instance interprets the LLM‘s reasoning behavior using knowledge graphs (KGs) and graph attention networks (GAT), and includes explanations of LLMs such as the decoder-only Llama-3 and the encoder-only RoBERTa. XplainLLM also features a framework for generating grounded explanations and the debugger-scores for multidimensional quality analysis. Our explanations include why-choose and why-not-choose components, reason-elements, and debugger-scores that collectively illuminate the LLM‘s reasoning behavior. Our evaluations demonstrate XplainLLM‘s potential to reduce hallucinations and improve grounded explanation generation in LLMs. XplainLLM is a resource for researchers and practitioners to build trust and verify the reliability of LLM outputs. Our code and dataset are publicly available.
%R 10.18653/v1/2024.emnlp-main.432
%U https://aclanthology.org/2024.emnlp-main.432/
%U https://doi.org/10.18653/v1/2024.emnlp-main.432
%P 7578-7596
Markdown (Informal)
[XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs](https://aclanthology.org/2024.emnlp-main.432/) (Chen et al., EMNLP 2024)
ACL