AnalysisBank is a library that captures expert financial analysis by pairing data signals with analytical moves and the corresponding expert text spans. The system matches input signals to these library entries during inference, enabling the generation of reports that are grounded in data-derived insights rather than generic structural templates. Experiments on financial benchmarks show that AnalysisBank produces 1.7–3.7 times more novel, data‑grounded insights than structural baselines, and the approach also transfers to scientific writing.
arXiv:2602. 07294v4 Announce Type: replace-cross Abstract: With the increasing deployment of Large Language Models (LLMs) in the finance domain, LLMs are increasingly expected to parse complex regulatory disclosures.
FinMultiHopQA is a new benchmark comprising 15,600 financial questions that require multi‑hop reasoning across filing sections, fiscal years, and peer companies. It is grounded in FinReflectKG, a temporally indexed financial knowledge graph with over 17.5 million triples derived from SEC 10‑K filings. The benchmark uniquely supports controlled multi‑hop taxonomies, document topologies, motif‑level reproducibility, and provenance‑linked auditability, and it allows researchers to test how different evidence presentations affect large language model performance.
arXiv:2608. 04374v1 Announce Type: cross Abstract: Large language models can produce fluent financial analysis, but fluency alone does not establish whether a report is suitable for institutional delivery.
arXiv:2606. 18192v1 Announce Type: new Abstract: As high-quality public web corpora become increasingly exhausted, clean long-context documents have become a scarce and expensive source of training data for large language models (LLMs).
arXiv:2609.35864v1 Announce Type: new Abstract: SEC 10-K filings contain substantial financial information that is not consistently captured in structured datasets, creating a missing-data problem af...
FIRME (Fusion and Identity Registry for Memory Evolution) is a registry‑anchored memory graph designed to integrate investor observations across time and sources while preserving identity, provenance, and context. It reconciles varying surface forms of recurring observations into canonical relationships, fuses investor‑call discussions with portfolio cash‑flow signals within periods, and uses persistent aliases to maintain consistent relationship histories across periods. Evaluations on proprietary investor‑call data, cash‑flow records, and S&P 500 earnings‑call transcripts show that FIRME improves Correct Match Rate by 7.8–16.5 percentage points and significantly enhances reattachment recall and merge precision compared to a baseline registry lacking alias memory.
arXiv:2609.25192v1 Announce Type: new Abstract: Financial search is a highly demanding task for LLM agents, requiring not only a correct final answer but also temporally valid information retrieval,...
FIRME is a registry‑anchored memory graph designed to integrate investor knowledge across multiple sources and time periods while preserving identity, provenance, and context. It reconciles varying surface forms of observations into canonical relationships, fuses investor‑call discussions with portfolio cash‑flow signals within periods, and uses persistent aliases to maintain consistent relationship histories across periods. Evaluation on proprietary investor‑call data and S&P 500 earnings‑call transcripts shows significant improvements in Correct Match Rate and reattachment‑recall compared to a baseline registry.
The paper examines how generative AI (GenAI) changes the way financial analysts produce information, using the 2023 integration of GenAI into FACTSET as a natural experiment. It finds that FACTSET reports become richer—adding 26% more distinct sources, 24% broader topics, and 21% more analytical methods—while also being more timely. However, the increased information load leads to lower forecast accuracy for analysts, suggesting a human attention bottleneck, whereas a machine-learning benchmark does not suffer the same decline.
arXiv:2610.19240v1 Announce Type: new Abstract: Financial disclosures express the underlying relationships of double-entry accounting through unstructured text. While financial LLM benchmarks predomi...
The paper introduces a benchmark for evaluating large language models on trustworthy analysis of earnings call transcripts. It proposes a numeric evidence evaluation method that assesses groundedness without expert annotation, and presents an automated pipeline that builds the ECTs-100 dataset from the top 100 S&P 500 constituents. The study also explores the failure mode of conscious incompetence, where models must recognize insufficient evidence and avoid hallucinations, finding that while groundedness is strong, correctness remains a challenge.
arXiv:2606. 03918v1 Announce Type: new Abstract: AI agents can increasingly handle the mechanical tasks of financial analysis: retrieving documents, calculating formulas, updating spreadsheets.