@inproceedings{weber-etal-2024-interpretability,
title = "Interpretability of Language Models via Task Spaces",
author = "Weber, Lucas and
Jumelet, Jaap and
Bruni, Elia and
Hupkes, Dieuwke",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.248",
pages = "4522--4538",
abstract = "The usual way to interpret language models (LMs) is to test their performance on different benchmarks and subsequently infer their internal processes.In this paper, we present an alternative approach, concentrating on the {\_}quality{\_} of LM processing, with a focus on their language abilities.To this end, we construct {`}linguistic task spaces{'} {--} representations of an LM{'}s language conceptualisation {--} that shed light on the connections LMs draw between language phenomena.Task spaces are based on the interactions of the learning signals from different linguistic phenomena, which we assess via a method we call {`}similarity probing{'}.To disentangle the learning signals of linguistic phenomena, we further introduce a method called {`}fine-tuning via gradient differentials{'} (FTGD).We apply our methods to language models of three different scales and find that larger models generalise better to overarching general concepts for linguistic tasks, making better use of their shared structure. Further, the distributedness of linguistic processing increases with pre-training through increased parameter sharing between related linguistic tasks. The overall generalisation patterns are mostly stable throughout training and not marked by incisive stages, potentially explaining the lack of successful curriculum strategies for LMs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="weber-etal-2024-interpretability">
<titleInfo>
<title>Interpretability of Language Models via Task Spaces</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lucas</namePart>
<namePart type="family">Weber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaap</namePart>
<namePart type="family">Jumelet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elia</namePart>
<namePart type="family">Bruni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dieuwke</namePart>
<namePart type="family">Hupkes</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>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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 usual way to interpret language models (LMs) is to test their performance on different benchmarks and subsequently infer their internal processes.In this paper, we present an alternative approach, concentrating on the _quality_ of LM processing, with a focus on their language abilities.To this end, we construct ‘linguistic task spaces’ – representations of an LM’s language conceptualisation – that shed light on the connections LMs draw between language phenomena.Task spaces are based on the interactions of the learning signals from different linguistic phenomena, which we assess via a method we call ‘similarity probing’.To disentangle the learning signals of linguistic phenomena, we further introduce a method called ‘fine-tuning via gradient differentials’ (FTGD).We apply our methods to language models of three different scales and find that larger models generalise better to overarching general concepts for linguistic tasks, making better use of their shared structure. Further, the distributedness of linguistic processing increases with pre-training through increased parameter sharing between related linguistic tasks. The overall generalisation patterns are mostly stable throughout training and not marked by incisive stages, potentially explaining the lack of successful curriculum strategies for LMs.</abstract>
<identifier type="citekey">weber-etal-2024-interpretability</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.248</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>4522</start>
<end>4538</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Interpretability of Language Models via Task Spaces
%A Weber, Lucas
%A Jumelet, Jaap
%A Bruni, Elia
%A Hupkes, Dieuwke
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F weber-etal-2024-interpretability
%X The usual way to interpret language models (LMs) is to test their performance on different benchmarks and subsequently infer their internal processes.In this paper, we present an alternative approach, concentrating on the _quality_ of LM processing, with a focus on their language abilities.To this end, we construct ‘linguistic task spaces’ – representations of an LM’s language conceptualisation – that shed light on the connections LMs draw between language phenomena.Task spaces are based on the interactions of the learning signals from different linguistic phenomena, which we assess via a method we call ‘similarity probing’.To disentangle the learning signals of linguistic phenomena, we further introduce a method called ‘fine-tuning via gradient differentials’ (FTGD).We apply our methods to language models of three different scales and find that larger models generalise better to overarching general concepts for linguistic tasks, making better use of their shared structure. Further, the distributedness of linguistic processing increases with pre-training through increased parameter sharing between related linguistic tasks. The overall generalisation patterns are mostly stable throughout training and not marked by incisive stages, potentially explaining the lack of successful curriculum strategies for LMs.
%U https://aclanthology.org/2024.acl-long.248
%P 4522-4538
Markdown (Informal)
[Interpretability of Language Models via Task Spaces](https://aclanthology.org/2024.acl-long.248) (Weber et al., ACL 2024)
ACL
- Lucas Weber, Jaap Jumelet, Elia Bruni, and Dieuwke Hupkes. 2024. Interpretability of Language Models via Task Spaces. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4522–4538, Bangkok, Thailand. Association for Computational Linguistics.