@inproceedings{bao-etal-2024-decoding,
title = "Decoding Matters: Addressing Amplification Bias and Homogeneity Issue in Recommendations for Large Language Models",
author = "Bao, Keqin and
Zhang, Jizhi and
Zhang, Yang and
Huo, Xinyue and
Chen, Chong and
Feng, Fuli",
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.589",
doi = "10.18653/v1/2024.emnlp-main.589",
pages = "10540--10552",
abstract = "Adapting Large Language Models (LLMs) for recommendation requires careful consideration of the decoding process, given the inherent differences between generating items and natural language. Existing approaches often directly apply LLMs{'} original decoding methods. However, we find these methods encounter significant challenges: 1) amplification bias{---}where standard length normalization inflates scores for items containing tokens with generation probabilities close to 1 (termed ghost tokens), and 2) homogeneity issue{---}generating multiple similar or repetitive items for a user. To tackle these challenges, we introduce a new decoding approach named Debiasing-Diversifying Decoding ($D^3$). $D^3$ disables length normalization for ghost tokens to alleviate amplification bias, and it incorporates a text-free assistant model to encourage tokens less frequently generated by LLMs for counteracting recommendation homogeneity. Extensive experiments on real-world datasets demonstrate the method{'}s effectiveness in enhancing accuracy and diversity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bao-etal-2024-decoding">
<titleInfo>
<title>Decoding Matters: Addressing Amplification Bias and Homogeneity Issue in Recommendations for Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Keqin</namePart>
<namePart type="family">Bao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jizhi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyue</namePart>
<namePart type="family">Huo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fuli</namePart>
<namePart type="family">Feng</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>Adapting Large Language Models (LLMs) for recommendation requires careful consideration of the decoding process, given the inherent differences between generating items and natural language. Existing approaches often directly apply LLMs’ original decoding methods. However, we find these methods encounter significant challenges: 1) amplification bias—where standard length normalization inflates scores for items containing tokens with generation probabilities close to 1 (termed ghost tokens), and 2) homogeneity issue—generating multiple similar or repetitive items for a user. To tackle these challenges, we introduce a new decoding approach named Debiasing-Diversifying Decoding (D³). D³ disables length normalization for ghost tokens to alleviate amplification bias, and it incorporates a text-free assistant model to encourage tokens less frequently generated by LLMs for counteracting recommendation homogeneity. Extensive experiments on real-world datasets demonstrate the method’s effectiveness in enhancing accuracy and diversity.</abstract>
<identifier type="citekey">bao-etal-2024-decoding</identifier>
<identifier type="doi">10.18653/v1/2024.emnlp-main.589</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.589</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>10540</start>
<end>10552</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Decoding Matters: Addressing Amplification Bias and Homogeneity Issue in Recommendations for Large Language Models
%A Bao, Keqin
%A Zhang, Jizhi
%A Zhang, Yang
%A Huo, Xinyue
%A Chen, Chong
%A Feng, Fuli
%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 bao-etal-2024-decoding
%X Adapting Large Language Models (LLMs) for recommendation requires careful consideration of the decoding process, given the inherent differences between generating items and natural language. Existing approaches often directly apply LLMs’ original decoding methods. However, we find these methods encounter significant challenges: 1) amplification bias—where standard length normalization inflates scores for items containing tokens with generation probabilities close to 1 (termed ghost tokens), and 2) homogeneity issue—generating multiple similar or repetitive items for a user. To tackle these challenges, we introduce a new decoding approach named Debiasing-Diversifying Decoding (D³). D³ disables length normalization for ghost tokens to alleviate amplification bias, and it incorporates a text-free assistant model to encourage tokens less frequently generated by LLMs for counteracting recommendation homogeneity. Extensive experiments on real-world datasets demonstrate the method’s effectiveness in enhancing accuracy and diversity.
%R 10.18653/v1/2024.emnlp-main.589
%U https://aclanthology.org/2024.emnlp-main.589
%U https://doi.org/10.18653/v1/2024.emnlp-main.589
%P 10540-10552
Markdown (Informal)
[Decoding Matters: Addressing Amplification Bias and Homogeneity Issue in Recommendations for Large Language Models](https://aclanthology.org/2024.emnlp-main.589) (Bao et al., EMNLP 2024)
ACL