@inproceedings{shu-yu-2024-distribution,
title = "Distribution Shifts Are Bottlenecks: Extensive Evaluation for Grounding Language Models to Knowledge Bases",
author = "Shu, Yiheng and
Yu, Zhiwei",
editor = "Falk, Neele and
Papi, Sara and
Zhang, Mike",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-srw.7",
pages = "71--88",
abstract = "Grounding language models (LMs) to knowledge bases (KBs) helps to obtain rich and accurate facts. However, it remains challenging because of the enormous size, complex structure, and partial observability of KBs. One reason is that current benchmarks fail to reflect robustness challenges and fairly evaluate models.This paper analyzes whether these robustness challenges arise from distribution shifts, including environmental, linguistic, and modal aspects.This affects the ability of LMs to cope with unseen schema, adapt to language variations, and perform few-shot learning. Thus, the paper proposes extensive evaluation protocols and conducts experiments to demonstrate that, despite utilizing our proposed data augmentation method, both advanced small and large language models exhibit poor robustness in these aspects. We conclude that current LMs are too fragile to navigate in complex environments due to distribution shifts. This underscores the need for future research focusing on data collection, evaluation protocols, and learning paradigms.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shu-yu-2024-distribution">
<titleInfo>
<title>Distribution Shifts Are Bottlenecks: Extensive Evaluation for Grounding Language Models to Knowledge Bases</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yiheng</namePart>
<namePart type="family">Shu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiwei</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Neele</namePart>
<namePart type="family">Falk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Papi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Grounding language models (LMs) to knowledge bases (KBs) helps to obtain rich and accurate facts. However, it remains challenging because of the enormous size, complex structure, and partial observability of KBs. One reason is that current benchmarks fail to reflect robustness challenges and fairly evaluate models.This paper analyzes whether these robustness challenges arise from distribution shifts, including environmental, linguistic, and modal aspects.This affects the ability of LMs to cope with unseen schema, adapt to language variations, and perform few-shot learning. Thus, the paper proposes extensive evaluation protocols and conducts experiments to demonstrate that, despite utilizing our proposed data augmentation method, both advanced small and large language models exhibit poor robustness in these aspects. We conclude that current LMs are too fragile to navigate in complex environments due to distribution shifts. This underscores the need for future research focusing on data collection, evaluation protocols, and learning paradigms.</abstract>
<identifier type="citekey">shu-yu-2024-distribution</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-srw.7</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>71</start>
<end>88</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Distribution Shifts Are Bottlenecks: Extensive Evaluation for Grounding Language Models to Knowledge Bases
%A Shu, Yiheng
%A Yu, Zhiwei
%Y Falk, Neele
%Y Papi, Sara
%Y Zhang, Mike
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F shu-yu-2024-distribution
%X Grounding language models (LMs) to knowledge bases (KBs) helps to obtain rich and accurate facts. However, it remains challenging because of the enormous size, complex structure, and partial observability of KBs. One reason is that current benchmarks fail to reflect robustness challenges and fairly evaluate models.This paper analyzes whether these robustness challenges arise from distribution shifts, including environmental, linguistic, and modal aspects.This affects the ability of LMs to cope with unseen schema, adapt to language variations, and perform few-shot learning. Thus, the paper proposes extensive evaluation protocols and conducts experiments to demonstrate that, despite utilizing our proposed data augmentation method, both advanced small and large language models exhibit poor robustness in these aspects. We conclude that current LMs are too fragile to navigate in complex environments due to distribution shifts. This underscores the need for future research focusing on data collection, evaluation protocols, and learning paradigms.
%U https://aclanthology.org/2024.eacl-srw.7
%P 71-88
Markdown (Informal)
[Distribution Shifts Are Bottlenecks: Extensive Evaluation for Grounding Language Models to Knowledge Bases](https://aclanthology.org/2024.eacl-srw.7) (Shu & Yu, EACL 2024)
ACL