Original title: Zkoumání reprezentace plurálu ve velkých jazykových modelech prostřednictvím sondovacích intervencí
Translated title: Investigating Large Language Models' Representations Of Plurality Through Probing Interventions
Authors: Hanna, Michael ; Mareček, David (advisor) ; Helcl, Jindřich (referee)
Document type: Master’s theses
Year: 2022
Language: eng
Abstract: Title: Investigating Large Language Models' Representations Of Plurality Through Probing Interventions Author: Michael Hanna Institute: Institute of Formal and Applied Linguistics Supervisor: RNDr. David Mareček, Ph.D., Institute of Formal and Applied Linguistics Abstract: Large language models (LLMs) have become ubiquitous in natural language processing, but how exactly they process their input and arrive at good downstream task performance is still poorly understood. While much work has been done using probing to examine LLM internals, or behavioral studies, to determine LLMs' linguistic capabilities, these techniques are too weak to allow us to draw conclusions how LLMs process language. In this paper, I use both probing and causal intervention methods to investigate the question of subject-verb agreement with respect to the subject's plurality. I find that while probing reveals that subject plurality information is distributed throughout a sentence, causal interventions suggest that only information stored in linguistically relevant tokens is used. Probing interventions suggest that some but not all probes capture information in a way that reflects LLMs' usage thereof. Keywords: Interpretability, Probing, Natural Language Processing, Computational Linguistics
Keywords: probing|interpretation|language model|neural network; probing|interpretace|jazykový model|neuronová síť

Institution: Charles University Faculties (theses) (web)
Document availability information: Available in the Charles University Digital Repository.
Original record: http://hdl.handle.net/20.500.11956/175532

Permalink: http://www.nusl.cz/ntk/nusl-508756


The record appears in these collections:
Universities and colleges > Public universities > Charles University > Charles University Faculties (theses)
Academic theses (ETDs) > Master’s theses
 Record created 2022-09-28, last modified 2024-01-26


No fulltext
  • Export as DC, NUŠL, RIS
  • Share