Aligning LLMs to Quote from Pre-Training Data (Quote-Tuning)
Quote-Tuning aligns LLMs to quote verbatim from trusted pre-training sources, turning the attribution step from post-hoc fact-checking into a built-in model behavior.
Ask this paper
Membership inference at train time: A fast membership-inference function checks whether generated spans exist verbatim in a trusted corpus, producing a reward signal without any human annotation.
Preference-based alignment: The authors build a synthetic preference dataset (quoted vs non-quoted outputs) and align the model with preference optimization, teaching it when to quote.
Strong verbatim gains: Quote-Tuning achieves up to a 130% relative increase in verbatim quotes from high-quality documents while preserving response quality across tasks, domains, and model families.
Verification advantage: Because quoted passages can be matched exactly to the source, downstream verification becomes trivial, helping regulated domains like medicine, law, and journalism.