Metraipolis › archive › dc_643dacf495d5
Reading Is Not Using: Retrieval, Judgment, and the Design of AI Financial Research Workflows — arXiv:2608.24842
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.24842
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T06:20:22.474Z
- SHA-256 of the archived text
b2a9a639e9213e5c93a18768ba749951854bf6636417915ead7e7c0fcf4dbfdc- Stable URL of this page
https://metraipolis.com/documento/dc_643dacf495d5
How to cite
Reading Is Not Using: Retrieval, Judgment, and the Design of AI Financial Research Workflows — arXiv:2608.24842 — arXiv (en), https://arxiv.org/abs/2608.24842 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_643dacf495d5 (Metraipolis archive dc_643dacf495d5, sha256 b2a9a639e9213e5c93a18768ba749951854bf6636417915ead7e7c0fcf4dbfdc)
BibTeX
@misc{dc643dacf495d5,
title = {Reading Is Not Using: Retrieval, Judgment, and the Design of AI Financial Research Workflows — arXiv:2608.24842},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.24842},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_643dacf495d5; sha256 b2a9a639e9213e5c93a18768ba749951854bf6636417915ead7e7c0fcf4dbfdc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.24842. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) are increasingly deployed as AI analysts to process financial disclosures and support AI-assisted investment decisions. Yet such systems are usually evaluated by what they can retrieve, not whether retrieved information affects their judgments. We identify a retrieval-integration gap in long-context financial analysis. Holding focal-firm information fixed and varying only unrelated context from 2,000 to 128,000 tokens, we find that a risk disclosure's influence on investment judgments falls to the experimental noise floor even as direct retrieval remains accurate. The pattern replicates across model families and judgment tasks and in experiments removing real disclosures from actual 10-K filings. More capable models postpone but do not eliminate the gap. Causal memory interventions show that compressed summaries and source-text lookup jointly transmit disclosures into judgments. Workflow architecture determines whether this transmission succeeds: chunk-and-summarize pipelines evict relevant information, whereas a targeted, structured restatement adjacent to the decision restores its influence. AI analyst performance is therefore jointly determined by model capability and workflow architecture. Retrieval-based evaluations can certify systems whose investment judgments ignore information they demonstrably retrieved. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.24842 — 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 2026-10-18T06:17:29.385Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).