6 papers · 1 filter
Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining
Deniz Bayazit, Aaron Mueller, Antoine Bosselut
Large language models (LLMs) learn non-trivial abstractions during pretraining, such as detecting irregular plural noun subjects. However, because traditional evaluation methods (e…
Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data Selection
Joe Stacey, Lisa Alazraki, Aran Ubhi +3
We investigate the robustness of fine-tuned Large Language Models (LLMs) for the task of Natural Language Inference (NLI), finding that the in-distribution gains from fine-tuning c…
Measuring Mechanistic Independence: Can Bias Be Removed Without Erasing Demographics?
Zhengyang Shan, Aaron Mueller
We investigate how independent demographic bias mechanisms are from general demographic recognition in language models. Using a multi-task evaluation setup where demographics are a…
Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages
Jannik Brinkmann, Chris Wendler, Christian Bartelt +1
Human bilinguals often use similar brain regions to process multiple languages, depending on when they learned their second language and their proficiency. In large language models…
Characterizing the Role of Similarity in the Property Inferences of Language Models
Juan Diego Rodriguez, Aaron Mueller, Kanishka Misra
Property inheritance -- a phenomenon where novel properties are projected from higher level categories (e.g., birds) to lower level ones (e.g., sparrows) -- provides a unique windo…
Disjoint Processing Mechanisms of Hierarchical and Linear Grammars in Large Language Models
Aruna Sankaranarayanan, Dylan Hadfield-Menell, Aaron Mueller
All natural languages are structured hierarchically. In humans, this structural restriction is neurologically coded: when two grammars are presented with identical vocabularies, br…