2 papers
cs.CL2026
Algorithmic Blindness in Large Language Models: A Calibration Study of Performance Prediction
Sohan Venkatesh, Ashish Mahendran Kurapath, Tejas Melkote
Large language models (LLMs) demonstrate remarkable breadth of knowledge, yet their ability to reason about computational processes remains poorly understood. Closing this gap matt…
cs.LG2026
On the Non-Identifiability of Steering Vectors in Large Language Models
Sohan Venkatesh, Ashish Mahendran Kurapath
Activation steering methods are widely used to control large language model (LLM) behavior and are often interpreted as revealing meaningful internal representations. This interpre…