Locate-then-edit succeeds at the same early-to-mid MLP locations in masked diffusion models as in autoregressive models, but requires optimization over intermediate partial-mask states to handle multi-token targets.
In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing , Houda Bouamor, Juan Pino, and Kalika Bali (Eds.)
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Norm-Anchor Scaling breaks the norm-feedback loop in sequential LLM editing by anchoring value vectors to original norms, improving long-run performance by 72.2% and extending the editing horizon over 4x.
LightEdit enables scalable lifelong knowledge editing in LLMs via selective knowledge retrieval and probability suppression during decoding, outperforming prior methods on ZSRE, Counterfact, and RIPE while reducing training costs.
JNO uses Pressure-Aware Coordination to jointly optimize neighborhood target representations under coupled constraints, improving propagation and preservation by at least 7% on RippleEdits while maintaining stability.
A survey reviewing benchmark data contamination in LLMs, its impact on evaluation, and alternative assessment approaches.
citing papers explorer
-
Norm Anchors Make Model Edits Last
Norm-Anchor Scaling breaks the norm-feedback loop in sequential LLM editing by anchoring value vectors to original norms, improving long-run performance by 72.2% and extending the editing horizon over 4x.