Divergence Decoding steers LLM logits using small auxiliary models to unlearn specific data at inference time, outperforming baselines and generalizing to images.
ISBN 978-3-031-72672-9
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Divergence Decoding: Inference-Time Unlearning via Auxiliary Models
Divergence Decoding steers LLM logits using small auxiliary models to unlearn specific data at inference time, outperforming baselines and generalizing to images.