Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model

Modern language models (LMs) tend to memorize portions of their training data and reproduce verbatim spans. When the underlying sources are sensitive or copyright-protected, such reproduction raises issues of consent and compensation for creators and compliance risks for developers. We propose Anchored Decoding, a plug-and-play inference-time method for suppressing verbatim reproduction: it enables decoding from any risky LM trained on mixed-license data by keeping generation in bounded proximity to a permissively trained safe LM. Anchored Decoding does so by adaptively allocating a user-chosen information budget over the generation trajectory and enforcing per-step constraints that yield a sequence-level guarantee, enabling a tunable risk–utility trade-off. To make Anchored Decoding practically useful, we introduce a new permissively trained safe model (TinyComma 1.8B), as well as $\textrm{Anchored}\_{\textrm{Byte}}$ Decoding, a byte-level variant of our method that enables cross-vocabulary fusion via the ByteSampler (Hayase et al., 2025) framework. We evaluate our methods across six model pairs on long-form evaluations of copyright risk and utility. Anchored and $\textrm{Anchored}\_{\textrm{Byte}}$ Decoding define a new Pareto frontier, preserving near-original fluency and factuality while eliminating up to 75% of the measurable copying gap (averaged over six copying metrics) between the risky baseline and a safe reference, at a modest inference overhead.