2 papers
cs.LG2025
Steering Language Model Refusal with Sparse Autoencoders
Kyle O'Brien, David Majercak, Xavier Fernandes +7
Responsible deployment of language models requires mechanisms for refusing unsafe prompts while preserving model performance. While most approaches modify model weights through add…
cs.CL2024
From Medprompt to o1: Exploration of Run-Time Strategies for Medical Challenge Problems and Beyond
Harsha Nori, Naoto Usuyama, Nicholas King +4
Run-time steering strategies like Medprompt are valuable for guiding large language models (LLMs) to top performance on challenging tasks. Medprompt demonstrates that a general LLM…