3 papers
cs.CL2026
Can LLMs Anticipate Their Cruxes?
David Reber, James Reber, Ari Holtzman +1
To use language models to help us make decisions we would like to understand the rationale behind the language model's outputs. In principle, the language model provides its ration…
cs.LG2025
Dynamic Weight Grafting: Localizing Finetuned Factual Knowledge in Transformers
Todd Nief, David Reber, Sean Richardson +1
When an LLM learns a new fact during finetuning (e.g., new movie releases, newly elected pope, etc.), where does this information go? Are entities enriched with relation informatio…
cs.CL2024
RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals
David Reber, Sean Richardson, Todd Nief +2
Reward models are widely used as proxies for human preferences when aligning or evaluating LLMs. However, reward models are black boxes, and it is often unclear what, exactly, they…