Metraipolis › archive › dc_cd62b84e17d3

Post-Generation Verification Dominates Retrieval Optimization: A 2^4 Factorial Ablation of RAG Pipeline Features — arXiv:2609.35774

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35774
License (as archived)
CC0-1.0
Archived
2026-10-07T18:37:42.129Z
SHA-256 of the archived text
ce6232dcd344100771c2ed88bc6171e859fa1ac905d72c250e1966aa13a0dc83
Stable URL of this page
https://metraipolis.com/documento/dc_cd62b84e17d3

How to cite

Post-Generation Verification Dominates Retrieval Optimization: A 2^4 Factorial Ablation of RAG Pipeline Features — arXiv:2609.35774 — arXiv (en), https://arxiv.org/abs/2609.35774 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd62b84e17d3 (Metraipolis archive dc_cd62b84e17d3, sha256 ce6232dcd344100771c2ed88bc6171e859fa1ac905d72c250e1966aa13a0dc83)
BibTeX
@misc{dccd62b84e17d3,
  title = {Post-Generation Verification Dominates Retrieval Optimization: A 2^4 Factorial Ablation of RAG Pipeline Features — arXiv:2609.35774},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35774},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd62b84e17d3; sha256 ce6232dcd344100771c2ed88bc6171e859fa1ac905d72c250e1966aa13a0dc83},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35774. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern RAG pipelines stack many enhancement features, but these features are typically validated in isolation, leaving their interactions unmeasured. We run a 2^4 full factorial ablation of four pipeline features: section expansion (SE), agentic search (AS), completeness check (CC), and table-of-contents-guided retrieval (ToC). The design crosses 16 configurations, 24 queries spanning eight interaction types, and two cloud-class models (768 scored responses) on five public documents (78-492 pages), and every answer is scored against a verified reference. On this corpus and task, post-generation verification dominates: CC is the strongest feature (d=+0.48, p<0.001), improving accuracy, completeness, and usefulness simultaneously, and CC alone (4.31/5) outperforms every configuration without it, including the three-feature SE+AS+ToC (4.11). ToC yields a significant gain at zero additional LLM calls (d=+0.22); AS is small and unstable, helping some queries and harming others; SE is neutral. The highest-quality configuration roughly doubles baseline latency, producing a genuine quality-latency Pareto frontier of six configurations. Feature utility is strongly query-type dependent (CC reaches d=+0.83 on completeness-demanding queries), so single-query-type evaluations systematically mis-rank features. We conclude that verifying answers matters more than optimizing retrieval, and that factorial designs with diverse query types are necessary to evaluate RAG features.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.35774 — 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 2026-10-07T18:04:00.974Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).