Metraipolis › archive › dc_e78277e090ef

DiRAFT: Privacy-Aware Financial Transcript Synthesis from Aggregate Discourse Priors — arXiv:2610.40938

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40938
License (as archived)
CC0-1.0
Archived
2026-11-03T07:50:25.045Z
SHA-256 of the archived text
fe84bf194a5f3c7861331bc12ae07757161dfb00440be1a124a707cf89b6ce5f
Stable URL of this page
https://metraipolis.com/documento/dc_e78277e090ef

How to cite

DiRAFT: Privacy-Aware Financial Transcript Synthesis from Aggregate Discourse Priors — arXiv:2610.40938 — arXiv (en), https://arxiv.org/abs/2610.40938 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e78277e090ef (Metraipolis archive dc_e78277e090ef, sha256 fe84bf194a5f3c7861331bc12ae07757161dfb00440be1a124a707cf89b6ce5f)
BibTeX
@misc{dce78277e090ef,
  title = {DiRAFT: Privacy-Aware Financial Transcript Synthesis from Aggregate Discourse Priors — arXiv:2610.40938},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40938},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e78277e090ef; sha256 fe84bf194a5f3c7861331bc12ae07757161dfb00440be1a124a707cf89b6ce5f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40938. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Using customer conversations to train and evaluate financial language models raises confidentiality concerns because non-public financial facts can remain after direct identifiers are masked. Synthetic transcripts offer an alternative data source, but their discourse fidelity and residual confidentiality risks require assessment. We introduce DiRAFT (Discourse Realization from Aggregate First-order Transitions), which extracts financial concept graphs and records the order in which concepts are first introduced. It pools adjacent concept transitions across training records and samples new graph plans from aggregate transition, starting-concept, and plan-length priors. A discourse layer guides text realization without supplying an individual source passage or graph. We assess privacy-related risks through two complementary evaluations: corpus-level structural overlap and source-grounded checks for specific non-public investor facts. The structural assessment covers two financial corpora and three generation backends. The confidential-fact assessment uses human review of 1,400 investor-call outputs across seven strategies and two backends. We also evaluate transition fidelity, content recoverability, and trajectory diversity. Stochastic sampling provides a favorable balance between transition fidelity and structural overlap, with consistent advantages over greedy and top-3 on investor calls. The confidential-fact assessment likewise detects fewer matches for stochastic sampling than these alternatives on both backends covered by the fact assessment. These complementary assessments provide empirical evidence on residual confidentiality risks without establishing a formal guarantee.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.40938 — 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 2026-11-03T07:49:31.014Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).