Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Deep Learning Models Also Recall Features
Pierre Beckmann
Recent work in mechanistic interpretability has studied how large language models recall facts stored in their weights. This paper argues that factual recall points to something br…
cs.AI2026
SciR: A Controllable Benchmark for Scientific Reasoning in LLMs
Pierre Beckmann, Marco Valentino, Andre Freitas
Three paradigmatic forms of inference recur across scientific reasoning: deduction, induction, and causal abduction. Reliably evaluating LLMs on these in scientific settings is cur…