Sparse model diffing on task-agnostic text can flag which academic, safety, or behavioral categories a fine-tuned or unlearned LLM has unintentionally changed.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reviving Your MNEME: Predicting The Side Effects of LLM Unlearning and Fine-Tuning via Sparse Model Diffing
Sparse model diffing on task-agnostic text can flag which academic, safety, or behavioral categories a fine-tuned or unlearned LLM has unintentionally changed.