Skip to content
conftrace_

behavioral shift

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

fine-tuning effect (1) sparse model diffing (1) side effect prediction (1) sparse probing (1) model diffing (1) large language model (1) model auditing (1) statistical test (1) ood detection (1) out-of-distribution evaluation (1)

Papers

An Auditing Test to Detect Behavioral Shift in Language Models ICLR 2025 REVIVING YOUR MNEME: Predicting The Side Effects of LLM Unlearning and Fine-Tuning via Sparse Model Diffing EMNLP 2025