Showing cs.CLShow all
3 papers · 1 filter
cs.CL2025
Causal Interventions Reveal Shared Structure Across English Filler-Gap Constructions
Sasha Boguraev, Christopher Potts, Kyle Mahowald
Language Models (LMs) have emerged as powerful sources of evidence for linguists seeking to develop theories of syntax. In this paper, we argue that causal interpretability methods…
cs.CL2025
False Friends Are Not Foes: Investigating Vocabulary Overlap in Multilingual Language Models
Julie Kallini, Dan Jurafsky, Christopher Potts +1
Subword tokenizers trained on multilingual corpora naturally produce overlapping tokens across languages. Does token overlap facilitate cross-lingual transfer or instead introduce…
cs.CL2025
Base Models Beat Aligned Models at Randomness and Creativity
Peter West, Christopher Potts
Alignment has quickly become a default ingredient in LLM development, with techniques such as reinforcement learning from human feedback making models act safely, follow instructio…