3 papers
cs.AI2026
CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning
Linas Nasvytis, Simon Jerome Han, Ben Prystawski +3
Language models can use verifiable rewards to improve at a wide variety of reasoning tasks. However, both parametric (e.g. RLVR) and non-parametric (e.g. prompt optimization) appro…
cs.LG2025
Addressing divergent representations from causal interventions on neural networks
Satchel Grant, Simon Jerome Han, Alexa R. Tartaglini +1
A common approach to mechanistic interpretability is to causally manipulate model representations via targeted interventions in order to understand what those representations encod…
cs.CL2023
Inductive reasoning in humans and large language models
Simon J. Han, Keith Ransom, Andrew Perfors +1
The impressive recent performance of large language models has led many to wonder to what extent they can serve as models of general intelligence or are similar to human cognition.…