5 papers
Transcoder Adapters for Reasoning-Model Diffing
Nathan Hu, Jake Ward, Thomas Icard +1
While reasoning models are increasingly ubiquitous, the effects of reasoning training on a model's internal mechanisms remain poorly understood. In this work, we introduce transcod…
Counterfactual Simulation Training for Chain-of-Thought Faithfulness
Peter Hase, Christopher Potts
Inspecting Chain-of-Thought reasoning is among the most common means of understanding why an LLM produced its output. But well-known problems with CoT faithfulness severely limit w…
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…
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…
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…