The List / Categories
Reports and filings research works with long documents, accounting definitions and disclosures that change over time. This guide covers information extraction and analysis rather than providing investment or accounting advice.
Combine this guide with financial QA and RAG when building an evidence-grounded document workflow.
This paper demonstrates that GPT-4, when prompted with standardized financial statements and chain-of-thought reasoning, outperforms human analysts and matches specialized machine learning models in predicting earnings direction, generating actionable alpha in trading strategies.
Fin-R1 is a 7B-parameter financial reasoning LLM trained via supervised fine-tuning and Group Relative Policy Optimization on a distilled 60k-sample chain-of-thought dataset, achieving competitive benchmark performance and practical utility in compliance and robo-advisory tasks.
This paper demonstrates that GPT-3.5 summaries of corporate disclosures amplify sentiment and better explain stock market reactions than original texts, enabling a novel 'bloat' metric that predicts lower price efficiency and higher information asymmetry.
GPT-InvestAR demonstrates that LLM-generated insights from 10-K filings, when used as features in a non-negative linear regression model, can outperform the S&P 500 in annual stock selection with minimal transaction costs.
This study provides a comprehensive assessment of LLM consistency across five finance tasks, finding that while simple tasks are highly reproducible, complex tasks vary, yet aggregation strategies and downstream statistical robustness mitigate these inconsistencies.
TAT-LLM is a specialized 7B-70B LLM fine-tuned on a Step-wise Pipeline (Extractor, Reasoner, Executor) that outperforms GPT-4 and prior SOTA models on financial tabular-textual QA benchmarks like FinQA and TAT-QA.
SHIELD integrates LLM-driven schema induction with GCN-based prediction to accurately forecast EV battery supply chain disruptions, outperforming baseline models and direct LLM prompting.
Use to study tool-augmented XBRL analysis with retrieval and calculators.
The paper introduces the Financial Numeric Extreme Labelling (FNXL) dataset with 2,794 XBRL tags and benchmarks sequence labeling versus extreme classification pipelines, finding that while sequence labeling excels on frequent labels, the extreme classification pipeline better handles the long-tail distribution of rare accounting metrics.
Discovered through citation/reference expansion; connected to 3 source papers.
SEC-QA introduces a dynamic benchmark for multi-document financial QA using SEC filings, demonstrating that standard RAG fails on complex quantitative tasks while a program-of-thought approach with document selection significantly improves accuracy.
Discovered through citation/reference expansion; connected to 4 source papers.
The paper argues that standard accuracy benchmarks for financial LLM agents are insufficient and proposes a risk-centric auditing framework, SAEA, which reveals that high-performing agents still harbor critical safety vulnerabilities like hallucination and adversarial susceptibility.
The paper introduces LUEI, a lightweight unsupervised framework using LLMs and semantic similarity to identify supply chain risk contributing events in news without training data, achieving significantly higher accuracy than keyword-based or commercial alternatives.
FinAuditing introduces a taxonomy-structured benchmark using real XBRL filings to evaluate LLMs on semantic matching, relationship extraction, and mathematical reasoning, revealing significant gaps in cross-document consistency and numerical accuracy.
Discovered through citation/reference expansion; connected to 2 source papers.
SECQUE is a benchmark of 565 expert-written questions on SEC filings that evaluates LLMs on financial reasoning, with results showing GPT-4o leads but significant gaps remain in complex insight generation.
This paper introduces a benchmark and five-stage evaluation framework to assess LLMs' capabilities in automating financial statement audits, revealing that while models can detect errors, they struggle with accounting standard citations and table revisions.
EDINET-Bench evaluates LLMs on complex Japanese financial tasks like fraud detection and earnings forecasting, revealing that state-of-the-art models perform only marginally better than logistic regression, highlighting the need for richer reasoning scaffolding.
FinNLI is a novel benchmark dataset for Financial Natural Language Inference comprising 21,304 premise-hypothesis pairs from SEC filings, annual reports, and earnings calls, revealing that current LLMs struggle with financial reasoning and that instruction-tuned financial models often underperform general-domain baselines.
Discovered through citation/reference expansion; connected to 1 source papers.
The paper proposes a scalable framework using Cohere's Command-R+ LLM to extract, clean, and quantitatively rate SEC 10-K filings across confidence, environment, innovation, and people dimensions, enabling longitudinal and comparative corporate analysis.
This paper benchmarks five LLM variants within the LARD-SC framework for supply chain risk identification, demonstrating that GPT-4o variants achieve superior accuracy and lower false positive rates compared to earlier models when analyzing news about Apple's Tier 1 suppliers.
This study evaluates five major LLMs on 10-K Business sections using human, automated, and behavioral metrics, finding no single model dominates and highlighting significant inter-rater disagreement in qualitative assessments.
Finch introduces FinWorkBench, a benchmark of 172 real-world enterprise finance and accounting workflows sourced from Enron and other institutions, revealing that even top AI agents like GPT-5.1 Pro pass only 38.4% of complex, long-horizon spreadsheet tasks.
The paper introduces SEC-former, a bidirectional transformer fine-tuned to reconstruct standardized SEC 10-K item structures from unstructured filings, demonstrating improved document similarity and topic detection for downstream financial analysis.
Fin-RATE introduces a benchmark for evaluating LLMs on SEC filings through detail, cross-entity, and longitudinal tasks, revealing that performance degrades significantly in multi-document reasoning due to hallucinations and entity mismatches.
This paper introduces FinRpt, a benchmark and multi-agent framework for Equity Research Report generation, demonstrating that fine-tuned agents outperform single LLMs in producing professional, accurate financial reports.
FinTagging introduces a two-stage benchmark for XBRL tagging that decomposes the task into Financial Numeric Identification and Financial Concept Linking, revealing that while LLMs excel at extraction, they struggle significantly with fine-grained alignment to the full US-GAAP taxonomy.
HiFi-KPI introduces a large-scale dataset of 1.65M iXBRL-tagged paragraphs with unified taxonomies and contextual metadata, demonstrating that encoder-based models excel at classification while LLMs struggle with structured extraction, particularly regarding date normalization.
The paper introduces FinAR-Bench, a benchmark evaluating LLMs on financial statement analysis through information extraction, indicator computation, and logical reasoning, revealing that while large models excel at extraction, they struggle with precise numerical calculation despite improved reasoning capabilities.
Discovered through citation/reference expansion; connected to 3 source papers.
This study proposes a lightweight, tiered text comparison framework using TF-IDF, BM25, and historical consistency analysis to detect semantic mismatches in XBRL tag mappings for SEC 10-K filings, revealing persistent industry-specific tagging heterogeneity and offering practical validation checkpoints for disclosure workflows.
The paper introduces FinLongDocQA, a benchmark for cross-table numerical reasoning in long financial reports, and proposes FinLongDocAgent, a multi-agent RAG system that significantly improves LLM accuracy by iteratively retrieving evidence and verifying calculations.
Discovered through citation/reference expansion; connected to 3 source papers.
Discovered through citation/reference expansion; connected to 2 source papers.
This paper demonstrates that LLM agents, by integrating textual disclosures with company-specific financial and operational context, can more accurately assess the materiality of physical climate risks in SEC filings than traditional keyword or embedding methods.
This paper presents a three-stage pipeline combining LLM extraction, embedding-based mapping, and LLM-as-a-judge validation to extract structured risk factors from 10-K filings into a hierarchical taxonomy, demonstrating autonomous taxonomy refinement and strong industry clustering validity.
This study quantifies the automation potential of equity research reports by mapping 4,964 sentences into 169 question archetypes, finding that 75% are automatable via text extraction or database queries, with LLMs successfully automating approximately 80% of statements when used in an ensemble.