Provenance Before Prose: Claim-Locked Reporting

The paper introduces claim‑locked reporting, a protocol that fixes the evidence source, numerical values, effect direction, and permissible language strength for each claim before a large language model (LLM) generates connective prose. This approach addresses failures where LLMs drift numbers or invert effect directions in scientific reports. Experiments on fMRI functional‑connectivity and randomized controlled trial reporting show that claim‑locked reporting improves reproducibility by 37.4 and 20.5 points over a deterministic hybrid template, while also reducing token usage and generation latency.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• llms