<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sia-etal-2024-anti">
    <titleInfo>
        <title>Anti-LM Decoding for Zero-shot In-context Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Suzanna</namePart>
        <namePart type="family">Sia</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexandra</namePart>
        <namePart type="family">DeLucia</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kevin</namePart>
        <namePart type="family">Duh</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>Zero-shot In-context learning is the phenomenon where models can perform a task given only the instructions. However, pre-trained large language models are known to be poorly calibrated for zero-shot tasks. One of the most effective approaches to handling this bias is to adopt a contrastive decoding objective, which accounts for the prior probability of generating the next token by conditioning on a context. This work introduces an Anti-Language Model objective with a decay factor designed to address the weaknesses of In-context Machine Translation. We conduct our experiments across 3 model types and sizes, 3 language directions, and for both greedy decoding and beam search. The proposed method outperforms other state-of-the-art decoding objectives, with up to 20 BLEU point improvement from the default objective in some settings.</abstract>
    <identifier type="citekey">sia-etal-2024-anti</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-naacl.216</url>
    </location>
    <part>
        <date>2024-06</date>
        <extent unit="page">
            <start>3403</start>
            <end>3420</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Anti-LM Decoding for Zero-shot In-context Machine Translation
%A Sia, Suzanna
%A DeLucia, Alexandra
%A Duh, Kevin
%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 sia-etal-2024-anti
%X Zero-shot In-context learning is the phenomenon where models can perform a task given only the instructions. However, pre-trained large language models are known to be poorly calibrated for zero-shot tasks. One of the most effective approaches to handling this bias is to adopt a contrastive decoding objective, which accounts for the prior probability of generating the next token by conditioning on a context. This work introduces an Anti-Language Model objective with a decay factor designed to address the weaknesses of In-context Machine Translation. We conduct our experiments across 3 model types and sizes, 3 language directions, and for both greedy decoding and beam search. The proposed method outperforms other state-of-the-art decoding objectives, with up to 20 BLEU point improvement from the default objective in some settings.
%U https://aclanthology.org/2024.findings-naacl.216
%P 3403-3420

Markdown (Informal)

[Anti-LM Decoding for Zero-shot In-context Machine Translation](https://aclanthology.org/2024.findings-naacl.216) (Sia et al., Findings 2024)

• Anti-LM Decoding for Zero-shot In-context Machine Translation (Sia et al., Findings 2024)

ACL

• Suzanna Sia, Alexandra DeLucia, and Kevin Duh. 2024. Anti-LM Decoding for Zero-shot In-context Machine Translation. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 3403–3420, Mexico City, Mexico. Association for Computational Linguistics.