资讯

FinVeriQA: Financial Research Agents for Question Answering: Routing, Retrieval, MCP Tool Use, and Provenance-Aware Evidence Verification

📅 2026-11-20 ⏱️ 约 7 分钟阅读 ✍️ AI导航编辑部 🔗 arxiv.org
FinVeriQA: Financial Research Agents for Question Answering: Routing, Retrieval, MCP Tool Use, and Provenance-Aware Evidence Verification
📝 内容摘要

Computer Science > Computation and Language [Submitted on 18 Nov 2026] Title:FinVeriQA: Financial Research Agents

📌 核心要点

  • Computer Science > Computation and Language
  • [Submitted on 18 Nov 2026]
  • From: Meenakshi Rajpurohit [view email][v1] Wed, 18 Nov 2026 19:13:45 UTC (406 KB)

Computer Science > Computation and Language

[Submitted on 18 Nov 2026]

Title:FinVeriQA: Financial Research Agents for Question Answering: Routing, Retrieval, MCP Tool Use, and Provenance-Aware Evidence Verification

View PDF HTML (experimental)Abstract:Large language models (LLMs) write fluent financial analyses but miscompute ratios, recall stale prices, and route questions to the wrong tool with high confidence. We ask which component should do each job in a financial question-answering assistant, and study it with FinVeriQA, an open-source multi-agent research prototype over SEC filings and live market data: a compact typed-decision model (Laya) routes each question and screens out advice requests, Python computes every number, retrieval and tools fetch evidence, Mistral-7B writes a cited answer, a code validator checks that cited IDs exist and that numbers match computed notes, and a Model Context Protocol (MCP) server exposes the pipeline. In live experiments, Laya routed better than Mistral-7B (0.85 vs. 0.52; overall 0.86 vs. 0.68, McNemar p = 0.0003); a 12B Mistral decided no better, and DeepSeek-R1-8B decided better (0.79 vs. 0.68, p = 0.0192) but about 9.9 times more slowly. Mistral-7B computed 29% of 100 financial calculations correctly against 100% for Python, a live quote cut price error from 210% to 0.00%, and hybrid retrieval reached 76% Hit@5 on 50 filing questions. Yet in a live case study, both agent answers passed validation while describing AMD sample data under NVIDIA's and Alphabet's names. A controlled upper-bound study on the FinRank benchmark explains why: when one figure in the shared evidence is corrupted, self-consistency stays confident (agreement 0.55 to 0.59 while accuracy falls from 0.50 to 0.00), and a shared-evidence check (the kind our validator performs) catches 35% of the errors, whereas a check against the original passage catches 77% ($p = 5.96 \times 10^{-8}$); for DeepSeek-R1-8B, 68% vs. 90%. Verification must be independent of the evidence the writer saw.

Submission history

From: Meenakshi Rajpurohit [view email][v1] Wed, 18 Nov 2026 19:13:45 UTC (406 KB)

Additional Features

Current browse context:

cs.CL

References & Citations

Loading...

Bibliographic and Citation Tools

Bibliographic Explorer (What is the Explorer?)

Connected Papers (What is Connected Papers?)

Litmaps (What is Litmaps?)

scite Smart Citations (What are Smart Citations?)

Code, Data and Media Associated with this Article

alphaXiv (What is alphaXiv?)

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub (What is DagsHub?)

Gotit.pub (What is GotitPub?)

Hugging Face (What is Huggingface?)

ScienceCast (What is ScienceCast?)

Demos

Recommenders and Search Tools

Influence Flower (What are Influence Flowers?)

CORE Recommender (What is CORE?)

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

来源arxiv.org· 本文为编辑整理,仅供参考