Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs
Keenan Pepper, Alex McKenzie, Florin Pop +6
Self-interpretation methods prompt language models to describe their own internal states, but remain unreliable due to hyperparameter sensitivity. We show that training lightweight…
cs.CL2024
Rethinking harmless refusals when fine-tuning foundation models
Florin Pop, Judd Rosenblatt, Diogo Schwerz de Lucena +1
In this paper, we investigate the degree to which fine-tuning in Large Language Models (LLMs) effectively mitigates versus merely conceals undesirable behavior. Through the lens of…