EvidenceLens: A Claim-Evidence Matrix for Auditing Financial Question Answering
Presentation
- Session
- Is the Model Even Thinking?
- Time
- - (US/Eastern) · session - Timezone
- Room
- America south
Abstract
Large language models are increasingly used to answer questions over annual reports, earnings decks, and analyst notes, yet their outputs remain difficult to verify in high-stakes financial workflows. A fluent answer can blend directly grounded statements, weak synthesis, and unsupported claims across narrative text, tables, and charts. We present EvidenceLens, a visual analytics prototype that treats financial question answering as a claim-evidence alignment problem. The system decomposes an answer into atomic claims, summarizes support composition and confidence--support gaps, and coordinates claim-level inspection with source passages, table cells, and chart regions. Its core representation is a multimodal claim-evidence matrix that exposes coverage, contradiction, and modality imbalance. To support reproducibility, we specify a JSON-based artifact schema, an inspectable multimodal alignment pipeline, and a deterministic review-priority ranking that maps backend signals into an auditable visual structure. Through two report-auditing scenarios, we illustrate how the interface makes grounded, weakly supported, and contradicted claims easier to inspect than in a linear chat transcript.
For Practitioners
Relevant practitioners include financial analysts, data scientists, fintech teams, and compliance/risk professionals. They can use this work to audit LLM-generated financial answers by checking each claim against text, tables, and charts.
