4 papers · 1 filter
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…
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…
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…
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…