Metraipolis › archive › dc_6ebbf285a746

From Chunks to Functional Evidence: Function-Aware Retrieval for EDA Documentation QA — arXiv:2610.09361

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09361
License (as archived)
CC0-1.0
Archived
2026-10-08T11:10:55.866Z
SHA-256 of the archived text
cb4e1b898419af70ce31f14bf5da888f205a4f13344ca0936d87f0b1580e63ec
Stable URL of this page
https://metraipolis.com/documento/dc_6ebbf285a746

How to cite

From Chunks to Functional Evidence: Function-Aware Retrieval for EDA Documentation QA — arXiv:2610.09361 — arXiv (en), https://arxiv.org/abs/2610.09361 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6ebbf285a746 (Metraipolis archive dc_6ebbf285a746, sha256 cb4e1b898419af70ce31f14bf5da888f205a4f13344ca0936d87f0b1580e63ec)
BibTeX
@misc{dc6ebbf285a746,
  title = {From Chunks to Functional Evidence: Function-Aware Retrieval for EDA Documentation QA — arXiv:2610.09361},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09361},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6ebbf285a746; sha256 cb4e1b898419af70ce31f14bf5da888f205a4f13344ca0936d87f0b1580e63ec},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09361. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Retrieval-Augmented Generation (RAG) is widely used to ground answers in documents. For complex technical documentation, however, the primary bottleneck is often not model reasoning but a mismatch between a query and the way knowledge is organized for retrieval. This mismatch is pronounced in Electronic Design Automation (EDA) documentation, where the information needed for an answer is scattered across heterogeneous yet tightly coupled artifacts. We therefore redesign the basic retrieval unit of RAG. Instead of operating on isolated chunks or binary relations, we collect typed artifacts into EDA functional units. Each unit is recorded as a hyperedge with links to its source chunks. We then train an encoder to align queries with functional units and combine unit retrieval with direct chunk retrieval. After mapping the selected units back to their sources, a unified reranker chooses the evidence given to the generator. On the newly constructed EDADocEval-QA dataset, our method improves ROUGE-L by 37.1% over Chunk RAG and 55.6% over the strongest graph baseline. On the public ORD-MMBench benchmark, it improves ROUGE-L by 30.0% over the strongest baseline. These results support function-aware evidence organization in the evaluated EDA documentation settings.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.09361 — 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 2026-10-08T10:14:06.080Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).