liu.seSearch for publications in DiVA
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Classifier Probes May Just Learn from Linear Context Features
Linköpings universitet, Institutionen för datavetenskap. Linköpings universitet, Tekniska fakulteten. (Natural Language Processing Group)
Linköpings universitet, Institutionen för datavetenskap, Interaktiva och kognitiva system. Linköpings universitet, Institutionen för datavetenskap, Artificiell intelligens och integrerade datorsystem. (Natural Language Processing Group)ORCID-id: 0000-0002-2492-9872
2020 (engelsk)Inngår i: Proceedings of the 28th International Conference on Computational Linguistics, 2020, Vol. 28, s. 5136-5146, artikkel-id 450Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Classifiers trained on auxiliary probing tasks are a popular tool to analyze the representations learned by neural sentence encoders such as BERT and ELMo. While many authors are aware of the difficulty to distinguish between “extracting the linguistic structure encoded in the representations” and “learning the probing task,” the validity of probing methods calls for further research. Using a neighboring word identity prediction task, we show that the token embeddings learned by neural sentence encoders contain a significant amount of information about the exact linear context of the token, and hypothesize that, with such information, learning standard probing tasks may be feasible even without additional linguistic structure. We develop this hypothesis into a framework in which analysis efforts can be scrutinized and argue that, with current models and baselines, conclusions that representations contain linguistic structure are not well-founded. Current probing methodology, such as restricting the classifier’s expressiveness or using strong baselines, can help to better estimate the complexity of learning, but not build a foundation for speculations about the nature of the linguistic structure encoded in the learned representations.

sted, utgiver, år, opplag, sider
2020. Vol. 28, s. 5136-5146, artikkel-id 450
Emneord [en]
Natural Language Processing, Machine Learning, Neural Language Representations
HSV kategori
Identifikatorer
URN: urn:nbn:se:liu:diva-175384DOI: 10.18653/v1/2020.coling-main.450OAI: oai:DiVA.org:liu-175384DiVA, id: diva2:1548430
Konferanse
International Conference on Computational Linguistics (COLING), Barcelona, Spain (Online), December 8–13, 2020
Tilgjengelig fra: 2021-04-30 Laget: 2021-04-30 Sist oppdatert: 2024-04-02bibliografisk kontrollert
Inngår i avhandling
1. Understanding Large Language Models: Towards Rigorous and Targeted Interpretability Using Probing Classifiers and Self-Rationalisation
Åpne denne publikasjonen i ny fane eller vindu >>Understanding Large Language Models: Towards Rigorous and Targeted Interpretability Using Probing Classifiers and Self-Rationalisation
2024 (engelsk)Doktoravhandling, med artikler (Annet vitenskapelig)
Abstract [en]

Large language models (LLMs) have become the base of many natural language processing (NLP) systems due to their performance and easy adaptability to various tasks. However, much about their inner workings is still unknown. LLMs have many millions or billions of parameters, and large parts of their training happen in a self-supervised fashion: They simply learn to predict the next word, or missing words, in a sequence. This is effective for picking up a wide range of linguistic, factual and relational information, but it implies that it is not trivial what exactly is learned, and how it is represented within the LLM. 

In this thesis, I present our work on methods contributing to better understanding LLMs. The work can be grouped into two approaches. The first lies within the field of interpretability, which is concerned with understanding the internal workings of the LLMs. Specifically, we analyse and refine a tool called probing classifiers that inspects the intermediate representations of LLMs, focusing on what roles the various layers of the neural model play. This helps us to get a global understanding of how information is structured in the model. I present our work on assessing and improving the probing methodologies. We developed a framework to clarify the limitations of past methods, showing that all common controls are insufficient. Based on this, we proposed more restrictive probing setups by creating artificial distribution shifts. We developed new metrics for the evaluation of probing classifiers that move the focus from the overall information that the layer contains to differences in information content across the LLM. 

The second approach is concerned with explainability, specifically with self-rationalising models that generate free-text explanations along with their predictions. This is an instance of local understandability: We obtain justifications for individual predictions. In this setup, however, the generation of the explanations is just as opaque as the generation of the predictions. Therefore, our work in this field focuses on better understanding the properties of the generated explanations. We evaluate the downstream performance of a classifier with explanations generated by different model pipelines and compare it to human ratings of the explanations. Our results indicate that the properties that increase the downstream performance differ from those that humans appreciate when evaluating an explanation. Finally, we annotate explanations generated by an LLM for properties that human explanations typically have and discuss the effects those properties have on different user groups. 

While a detailed understanding of the inner workings of LLMs is still unfeasible, I argue that the techniques and analyses presented in this work can help to better understand LLMs, the linguistic knowledge they encode and their decision-making process. Together with knowledge about the models’ architecture, training data and training objective, such techniques can help us develop a robust high-level understanding of LLMs that can guide decisions on their deployment and potential improvements. 

sted, utgiver, år, opplag, sider
Linköping: Linköping University Electronic Press, 2024. s. 81
Serie
Linköping Studies in Science and Technology. Dissertations, ISSN 0345-7524 ; 2364
HSV kategori
Identifikatorer
urn:nbn:se:liu:diva-201985 (URN)10.3384/9789180754712 (DOI)9789180754705 (ISBN)9789180754712 (ISBN)
Disputas
2024-04-18, Ada Lovelace, B-building, Campus Valla, Linköping, 14:00 (engelsk)
Opponent
Veileder
Tilgjengelig fra: 2024-04-02 Laget: 2024-04-02 Sist oppdatert: 2024-04-02bibliografisk kontrollert

Open Access i DiVA

fulltext(223 kB)111 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 223 kBChecksum SHA-512
5d5bb1e6ea9778846e3497bdbba4191db8fc929308abd8305595d6c43532148b8474bccdbab820375db77c49f39108dea37e5675c41b3ade2bd536fa39e2c56c
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fulltekst

Person

Kuhlmann, Marco

Søk i DiVA

Av forfatter/redaktør
Kunz, JennyKuhlmann, Marco
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 111 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 146 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf