Michael Hahn

Character-based Surprisal as a Model of Reading Difficulty in the Presence of Errors

2019

Intuitively, human readers cope easily with errors in text; typos, misspelling, word substitutions, etc. do not unduly disrupt natural reading. Previous work indicates that letter transpositions result in increased reading times, but it is unclear …

Contextualize-then-Aggregate: Circuits for In-Context Learning in Gemma-2 2B

2025 · arXiv (Cornell University)

In-Context Learning (ICL) is an intriguing ability of large language models (LLMs). Despite a substantial amount of work on its behavioral aspects and how it emerges in miniature setups, it remains unclear which mechanism assembles …