18 citations · 19 across the 10 of their papers we have counts for
3 papers · 1 filter
MechaTerp-TRACE: A Novel Approach for Component Ablation Analysis in Language Models
Brandon Colelough, Davis Bartels, Madeline Bittner +1
Interpretability research on large language models has produced accounts of factual recall in feed-forward layers and of token relationships in self-attention, but little work offe…
6.5% of the Neuro-Symbolic Literature Can Be Reproduced from Its Published Artifacts, a Six-Stage Audit Framework and First Instantiation
Brandon Colelough, Vladimir Martirosyan, Ishan Tamrakar +6
We present a six-stage framework for auditing the reproducibility of scientific claims across a research literature within the computer science domain, and instantiate our framewor…
Quantifying Hallucinations in Language Language Models on Medical Textbooks
Brandon C. Colelough, Davis Bartels, Dina Demner-Fushman
Hallucinations, the tendency for large language models to provide responses with factually incorrect and unsupported claims, is a serious problem within natural language processing…