Metraipolis › archive › dc_f775e69f8294
FinLifeBench: Exhaustive Life-Event History and Financial-State Reconstruction from Longitudinal Banking Dialogue — arXiv:2609.01198
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01198
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:32:22.161Z
- SHA-256 of the archived text
e8ded94585d8104ee68ffbe99397d0159e238850245c1b321aa5001053fba70e- Stable URL of this page
https://metraipolis.com/documento/dc_f775e69f8294
How to cite
FinLifeBench: Exhaustive Life-Event History and Financial-State Reconstruction from Longitudinal Banking Dialogue — arXiv:2609.01198 — arXiv (en), https://arxiv.org/abs/2609.01198 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f775e69f8294 (Metraipolis archive dc_f775e69f8294, sha256 e8ded94585d8104ee68ffbe99397d0159e238850245c1b321aa5001053fba70e)
BibTeX
@misc{dcf775e69f8294,
title = {FinLifeBench: Exhaustive Life-Event History and Financial-State Reconstruction from Longitudinal Banking Dialogue — arXiv:2609.01198},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01198},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f775e69f8294; sha256 e8ded94585d8104ee68ffbe99397d0159e238850245c1b321aa5001053fba70e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01198. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Repeated banking interactions require assistants to maintain complete, current, and traceable customer records as life changes emerge incidentally in routine requests. Existing benchmarks emphasize question answering, bounded episodes, or targeted recall rather than exhaustive longitudinal reconstruction. We introduce FinLifeBench, which evaluates two tasks over the same cumulative dialogue: reconstructing every life-event instance with its first-establishing session and reconstructing a complete 34-path financial state at consecutive checkpoints. The benchmark contains 6,000 eight-turn Korean banking sessions from 20 independent synthetic trajectories, with deterministic, exhaustive gold for 24 event types and 34 state paths and consensus quality assurance. Across eleven LLMs under a full-context condition, event-anchor recall falls from 0.591 at 15 sessions to 0.445 at 300. Errors are driven primarily by omitted events rather than poor anchor localization, while financial-state reconstruction frequently treats superseded or potentially outdated information as current; the best GCA@15 reaches 0.470. Performance on the two reconstruction tasks is only weakly associated. These results show that models can localize evidence for recovered events while still failing to maintain complete and temporally valid longitudinal records. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.01198 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T06:15:12.679Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).