liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A Hypothesis-Driven Framework for the Analysis of Self-Rationalising Models
Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, Faculty of Science & Engineering. University of Stuttgart, Fraunhofer IPA. (Natural Language Processing Group)
Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems. Linköping University, Faculty of Science & Engineering. (Natural Language Processing Group)ORCID iD: 0009-0006-1001-0546
2024 (English)In: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop / [ed] Falk N., Papi S., Zhang M., 2024, p. 148-161Conference paper, Published paper (Refereed)
Abstract [en]

The self-rationalising capabilities of LLMs are appealing because the generated explanations can give insights into the plausibility of the predictions. However, how faithful the explanations are to the predictions is questionable, raising the need to explore the patterns behind them further. To this end, we propose a hypothesis-driven statistical framework. We use a Bayesian network to implement a hypothesis about how a task (in our example, natural language inference) is solved, and its internal states are translated into natural language with templates. Those explanations are then compared to LLM-generated free-text explanations using automatic and human evaluations. This allows us to judge how similar the LLM’s and the Bayesian network’s decision processes are. We demonstrate the usage of our framework with an example hypothesis and two realisations in Bayesian networks. The resulting models do not exhibit a strong similarity to GPT-3.5. We discuss the implications of this as well as the framework’s potential to approximate LLM decisions better in future work.

Place, publisher, year, edition, pages
2024. p. 148-161
Keywords [en]
Computational linguistics
National Category
Language Technology (Computational Linguistics)
Identifiers
URN: urn:nbn:se:liu:diva-201911Scopus ID: 2-s2.0-85188732502ISBN: 9798891760905 (print)OAI: oai:DiVA.org:liu-201911DiVA, id: diva2:1847199
Conference
P18th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2024 - Student Research Workshop, SRW 2024 St. Julian's 21 March 2024 through 22 March 2024
Available from: 2024-03-26 Created: 2024-03-26 Last updated: 2024-08-20

Open Access in DiVA

fulltext(1210 kB)17 downloads
File information
File name FULLTEXT01.pdfFile size 1210 kBChecksum SHA-512
0e8aac2e9d531afb803c83de5c064b0f192a0468c26fab481600e1db48c3cab1efa185eec27eac7bc57d6b6589e6e8c251abf1b4004750645941fe52e8b6b7cd
Type fulltextMimetype application/pdf

Scopus

Authority records

Braun, MarcKunz, Jenny

Search in DiVA

By author/editor
Braun, MarcKunz, Jenny
By organisation
Artificial Intelligence and Integrated Computer SystemsFaculty of Science & Engineering
Language Technology (Computational Linguistics)

Search outside of DiVA

GoogleGoogle Scholar
Total: 17 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 134 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf