Reading Is Not Using: Retrieval, Judgment, and the Design of AI Financial Research Workflows
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.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 57%Mastering financial risk and compliance with AI -... - Technology Record →
- PossiblePossibly related (embedding) · 54%Situational Awareness, star AI hedge fund that nearly imploded, now being probed by the SEC →
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- FuzzySimilar title/name (fuzzy) · 59%argoproj/argo-workflows →
“Fuzzy title match (0.73): “Reading Is Not Using: Retrieval, Judgment, and the Design of” ≈ “argoproj/argo-workflows””
- FuzzySimilar title/name (fuzzy) · 59%google-research/google-research →
“Fuzzy title match (0.73): “Reading Is Not Using: Retrieval, Judgment, and the Design of” ≈ “google-research/google-research””
- LinkedLinked via arxiv author · 85%Miao Liu →
“Reading Is Not Using: Retrieval, Judgment, and the Design of AI Financial Research Workflows”
- LinkedLinked via arxiv author · 85%Zhizhe Liu →
“Reading Is Not Using: Retrieval, Judgment, and the Design of AI Financial Research Workflows”