2 papers
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…
cs.CL2024
Combining Domain-Specific Models and LLMs for Automated Disease Phenotyping from Survey Data
Gal Beeri, Benoit Chamot, Elena Latchem +4
This exploratory pilot study investigated the potential of combining a domain-specific model, BERN2, with large language models (LLMs) to enhance automated disease phenotyping from…