Skip to main content
Search

Wei Hou

1 related articles

Subscribe to updates
  1. arXiv

    Agent outputs now trace sentence by sentence: LMLineage tags each source out of band and compacts only documents that drift out of use

    LMLineage maps every output sentence of an LLM agent session to the input spans that support it, with calibrated confidence, without white-box access to the model or extra inference passes. It runs as an out-of-band service, matches by window-level embedding similarity, and uses that lineage to detect which input documents are no longer referenced, compacting only those while keeping user instructions verbatim. On 71 Chinese gold-annotated sentences, the greedy-window path reaches 0.725 mean fine-grained accuracy versus 0.497 for exhaustive line-matching; a separate 90 turns of multi-turn sessions across three generator models serve only latency and feasibility checks.

You’re all caught up