3 papers
cs.LG2026
Shaping capabilities with token-level data filtering
Neil Rathi, Alec Radford
Current approaches to reducing undesired capabilities in language models are largely post hoc, and can thus be easily bypassed by adversaries. A natural alternative is to shape cap…
cs.CL2025
Humans overrely on overconfident language models, across languages
Neil Rathi, Dan Jurafsky, Kaitlyn Zhou
As large language models (LLMs) are deployed globally, it is crucial that their responses are calibrated across languages to accurately convey uncertainty and limitations. Prior wo…
cs.CL2025
TopoLM: brain-like spatio-functional organization in a topographic language model
Neil Rathi, Johannes Mehrer, Badr AlKhamissi +3
Neurons in the brain are spatially organized such that neighbors on tissue often exhibit similar response profiles. In the human language system, experimental studies have observed…