Author

Sewoong Oh

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Feb 2026

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model

Anchored Decoding is proposed, a plug-and-play inference-time method for suppressing verbatim copying that enables decoding from any risky LM trained on mixed-license data by keeping generation in bounded proximity to a permissively trained safe LM.

Jacqueline He, J. Hayase, Wen-tau Yih et al. · arXiv.org · 0 citations