Metraipolis › archive › dc_2d5596bcd6fa

The Bottleneck Is Retrieval, Not Reading: Diagnosing Evidence-Based Generation with RAG for Long Context Question Answering — arXiv:2610.26951

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.26951
License (as archived): CC0-1.0
Archived: 2026-10-21T07:08:44.006Z
SHA-256 of the archived text: 838573b3c99a045f6d5512f5956c049db47820dabae8e4d590a709959baebb49
Stable URL of this page: https://metraipolis.com/documento/dc_2d5596bcd6fa

How to cite

The Bottleneck Is Retrieval, Not Reading: Diagnosing Evidence-Based Generation with RAG for Long Context Question Answering — arXiv:2610.26951 — arXiv (en), https://arxiv.org/abs/2610.26951 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2d5596bcd6fa (Metraipolis archive dc_2d5596bcd6fa, sha256 838573b3c99a045f6d5512f5956c049db47820dabae8e4d590a709959baebb49)

BibTeX

@misc{dc2d5596bcd6fa,
  title = {The Bottleneck Is Retrieval, Not Reading: Diagnosing Evidence-Based Generation with RAG for Long Context Question Answering — arXiv:2610.26951},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.26951},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2d5596bcd6fa; sha256 838573b3c99a045f6d5512f5956c049db47820dabae8e4d590a709959baebb49},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.26951. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Retrieval-augmented generation (RAG) is the dominant paradigm for grounding large language models in external corpora, but its similarity-driven, chunked pipeline has structural blind spots: it cannot anticipate which passages a question requires and discards document-level context that resolves cross-passage references. We introduce evidence-based generation (EBG), requiring models to return an answer with line-level citations, and a joint Ans+Evid metric that scores correctness and grounding simultaneously. We reformulate two corpora into evidence-grounded multi-document QA benchmarks- MultiHop-RAG and QASPER-MP, a multi-paper adaptation of QASPER with realistic short paper cues, and pair them with a controlled synthetic two-hop haystack and an evidence-augmented NoLiMa spanning 10K-1M characters. Across ten proprietary frontier and three open-weight LLMs, EBG isolates two RAG limitations that long-context models avoid: similarity retrieval surfaces any relevant chunk far more reliably than all required chunks for multi-fact queries, and chunking destroys document meta-information needed to resolve identity-bearing queries. EBG also exposes grounding failures invisible to answer-only evaluation, including incomplete citations in two-needle settings and a widening gap between Ans and Ans+Evid when context contradicts parametric knowledge. Data and code are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2610.26951 — 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 2026-10-21T07:05:58.089Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).