@inproceedings{zhou-etal-2024-latent,
title = "Latent Learningscape Guided In-context Learning",
author = "Zhou, Anlai and
Jiang, Sunshine and
Liu, Yifei and
Wu, Yiquan and
Kuang, Kun and
Xiao, Jun",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.482/",
doi = "10.18653/v1/2024.findings-acl.482",
pages = "8090--8101",
abstract = "The growing interest in leveraging large language models is driven by their exceptional imitation and reasoning capabilities. In-context learning (ICL), a streamlined method, has shown potential in boosting these models' performance without modifying their underlying parameters, especially when supplied with suitable demonstrations. However, existing methods mainly choose demonstrations by comparing surface-level semantic similarities (e.g., based on embedding) and fall short of identifying the most fitting ones. This paper introduces the concept of a {\textquotedblleft}latent learningscape{\textquotedblright}, a more nuanced representation that describes the characteristic of the demonstrations. Building on this concept, we develop a results-driven approach to characterize the latent learningscape features of demonstrations, which then inform the creation of more effective prompts. Through comprehensive testing across datasets in arithmetic, commonsense, and symbolic reasoning tasks, our approach outperforms leading models, showing an average increase in scores by 7.4 percentage points."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2024-latent">
<titleInfo>
<title>Latent Learningscape Guided In-context Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anlai</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunshine</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiquan</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Kuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The growing interest in leveraging large language models is driven by their exceptional imitation and reasoning capabilities. In-context learning (ICL), a streamlined method, has shown potential in boosting these models’ performance without modifying their underlying parameters, especially when supplied with suitable demonstrations. However, existing methods mainly choose demonstrations by comparing surface-level semantic similarities (e.g., based on embedding) and fall short of identifying the most fitting ones. This paper introduces the concept of a “latent learningscape”, a more nuanced representation that describes the characteristic of the demonstrations. Building on this concept, we develop a results-driven approach to characterize the latent learningscape features of demonstrations, which then inform the creation of more effective prompts. Through comprehensive testing across datasets in arithmetic, commonsense, and symbolic reasoning tasks, our approach outperforms leading models, showing an average increase in scores by 7.4 percentage points.</abstract>
<identifier type="citekey">zhou-etal-2024-latent</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.482</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.482/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>8090</start>
<end>8101</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Latent Learningscape Guided In-context Learning
%A Zhou, Anlai
%A Jiang, Sunshine
%A Liu, Yifei
%A Wu, Yiquan
%A Kuang, Kun
%A Xiao, Jun
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F zhou-etal-2024-latent
%X The growing interest in leveraging large language models is driven by their exceptional imitation and reasoning capabilities. In-context learning (ICL), a streamlined method, has shown potential in boosting these models’ performance without modifying their underlying parameters, especially when supplied with suitable demonstrations. However, existing methods mainly choose demonstrations by comparing surface-level semantic similarities (e.g., based on embedding) and fall short of identifying the most fitting ones. This paper introduces the concept of a “latent learningscape”, a more nuanced representation that describes the characteristic of the demonstrations. Building on this concept, we develop a results-driven approach to characterize the latent learningscape features of demonstrations, which then inform the creation of more effective prompts. Through comprehensive testing across datasets in arithmetic, commonsense, and symbolic reasoning tasks, our approach outperforms leading models, showing an average increase in scores by 7.4 percentage points.
%R 10.18653/v1/2024.findings-acl.482
%U https://aclanthology.org/2024.findings-acl.482/
%U https://doi.org/10.18653/v1/2024.findings-acl.482
%P 8090-8101
Markdown (Informal)
[Latent Learningscape Guided In-context Learning](https://aclanthology.org/2024.findings-acl.482/) (Zhou et al., Findings 2024)
ACL
- Anlai Zhou, Sunshine Jiang, Yifei Liu, Yiquan Wu, Kun Kuang, and Jun Xiao. 2024. Latent Learningscape Guided In-context Learning. In Findings of the Association for Computational Linguistics: ACL 2024, pages 8090–8101, Bangkok, Thailand. Association for Computational Linguistics.