Metraipolis › archive › dc_8ccfd258b4a0

Multimodal Requirements Traceability Link Recovery in Industrial Settings — arXiv:2610.34503

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.34503
License (as archived)
CC0-1.0
Archived
2026-10-27T08:01:27.533Z
SHA-256 of the archived text
a10c0339a1053283c4c2c916ecc90ba6280ab128d5dd2f5233456f4d26674775
Stable URL of this page
https://metraipolis.com/documento/dc_8ccfd258b4a0

How to cite

Multimodal Requirements Traceability Link Recovery in Industrial Settings — arXiv:2610.34503 — arXiv (en), https://arxiv.org/abs/2610.34503 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8ccfd258b4a0 (Metraipolis archive dc_8ccfd258b4a0, sha256 a10c0339a1053283c4c2c916ecc90ba6280ab128d5dd2f5233456f4d26674775)
BibTeX
@misc{dc8ccfd258b4a0,
  title = {Multimodal Requirements Traceability Link Recovery in Industrial Settings — arXiv:2610.34503},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.34503},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8ccfd258b4a0; sha256 a10c0339a1053283c4c2c916ecc90ba6280ab128d5dd2f5233456f4d26674775},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.34503. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Requirements traceability links support activities such as change-impact analysis, coverage checking, and validation. Industrial requirements can include traceable images, which text-only approaches cannot process directly. For a fixed classifier configuration, binary decisions alone offer no direct way to adjust the balance between missed and incorrect links. We extend a retrieval-augmented generation (RAG) approach for inter-requirements traceability link recovery (TLR). Our extension retrieves text and image candidates separately, classifies each retrieved pair with a vision-language model, and filters the predicted links by verbalized confidence. We evaluate our approach on three non-overlapping industrial requirement sets and six public text-only datasets. On the industrial test sets, our approach achieves an F1 score of 0.310, compared with 0.114 for our replication of the baseline approach by Hey et al. Our approach recovers links in all four modality combinations while improving text-only F1 on the industrial data and maintaining similar performance on the public datasets, but recovery remains limited by failures to retrieve related text requirements for image queries. Confidence filtering produces link sets with different precision and recall, removing false positives and some correctly recovered links from the unfiltered link set. This study provides industrial evidence on the potential and limitations of a current RAG-based TLR approach for multimodal requirements and identifies cross-modal retrieval as the component to prioritize in further optimization.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI); Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2610.34503 — 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 2026-10-27T07:55:30.908Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).