<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhan-etal-2024-self">
    <titleInfo>
        <title>Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Milan</namePart>
        <namePart type="family">Bhan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jean-Noël</namePart>
        <namePart type="family">Vittaut</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nicolas</namePart>
        <namePart type="family">Chesneau</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marie-Jeanne</namePart>
        <namePart type="family">Lesot</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>Incorporating natural language rationales in the prompt and In-Context Learning (ICL) have led to a significant improvement of Large Language Models (LLMs) performance. However, generating high-quality rationales require human-annotation or the use of auxiliary proxy models. In this work, we propose Self-AMPLIFY to automatically generate rationales from post hoc explanation methods applied to Small Language Models (SLMs) to improve their own performance. Self-AMPLIFY is a 3-step method that targets samples, generates rationales and builds a final prompt to leverage ICL. Self-AMPLIFY performance is evaluated on four SLMs and five datasets requiring strong reasoning abilities. Self-AMPLIFY achieves good results against competitors, leading to strong accuracy improvement. Self-AMPLIFY is the first method to apply post hoc explanation methods to autoregressive language models to generate rationales to improve their own performance in a fully automated manner.</abstract>
    <identifier type="citekey">bhan-etal-2024-self</identifier>
    <location>
        <url>https://aclanthology.org/2024.emnlp-main.615</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>10974</start>
            <end>10991</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations
%A Bhan, Milan
%A Vittaut, Jean-Noël
%A Chesneau, Nicolas
%A Lesot, Marie-Jeanne
%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 bhan-etal-2024-self
%X Incorporating natural language rationales in the prompt and In-Context Learning (ICL) have led to a significant improvement of Large Language Models (LLMs) performance. However, generating high-quality rationales require human-annotation or the use of auxiliary proxy models. In this work, we propose Self-AMPLIFY to automatically generate rationales from post hoc explanation methods applied to Small Language Models (SLMs) to improve their own performance. Self-AMPLIFY is a 3-step method that targets samples, generates rationales and builds a final prompt to leverage ICL. Self-AMPLIFY performance is evaluated on four SLMs and five datasets requiring strong reasoning abilities. Self-AMPLIFY achieves good results against competitors, leading to strong accuracy improvement. Self-AMPLIFY is the first method to apply post hoc explanation methods to autoregressive language models to generate rationales to improve their own performance in a fully automated manner.
%U https://aclanthology.org/2024.emnlp-main.615
%P 10974-10991

Markdown (Informal)

[Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations](https://aclanthology.org/2024.emnlp-main.615) (Bhan et al., EMNLP 2024)

• Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations (Bhan et al., EMNLP 2024)

ACL

• Milan Bhan, Jean-Noël Vittaut, Nicolas Chesneau, and Marie-Jeanne Lesot. 2024. Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 10974–10991, Miami, Florida, USA. Association for Computational Linguistics.