FinReflectKG - EvalBench benchmarks financial KG extraction from SEC 10-K filings.
problem Lack of universal benchmark and evaluation framework for financial KG construction.
method Agentic and holistic evaluation principles, deterministic commit-then-justify judging protocol, binary and ordinal evaluations.
result Reflection-based extraction outperforms single-pass extraction in comprehensiveness, precision, and relevance.
Narrative disclosures in 10-K filings improve bankruptcy prediction beyond accounting ratios.
problem Traditional bankruptcy prediction models rely on accounting ratios, which may not capture early warning signals.
method Developed a PB Stress Score based on distress-specific language in 10-K narratives, evaluated against accounting and dictionary benchmarks.
result Adding the PB Stress Score increases AUC from 0.8323 to 0.9019 and improves top-decile bankruptcy capture from 44.12% to 64.71%.
FinReflectKG builds a comprehensive financial knowledge graph from SEC filings, improving extraction quality.
problem Lack of large-scale, open-source financial knowledge graph datasets.
method Intelligent document parsing, table-aware chunking, schema-guided iterative extraction, reflection-driven feedback loop.
result Reflection-agent-based mode achieves best balance of efficiency, accuracy, and reliability.
The study improves sentiment analysis of 10-K filings, revealing aggregation effects on accuracy and correlation with market outcomes.
problem Lack of sentiment analysis for 10-K filings, particularly for risk disclosures.
method Supervised lexicon-learning approach applied to 10-K filings and Item 1A risk-factor sections, trained against return and volatility labels at different levels of aggregation.
result Sentiment analysis of Item 1A sections performs better at the individual-firm level, while full-filing text is more accurate at sector and portfolio levels.
IPO Finance Agent extends Finance Agent v2 for SpaceX S-1 filings, improving accuracy and cost-efficiency.
problem Evaluating IPO due diligence tasks with long-form documents.
method Extended task domain, improved agentic harness with contextual retrieval, automated rubric generation.
result Best-performing model reaches 79.8% accuracy, cost-efficient model at 77.2% with 0.05 USD per query.
New AI stock indices classify firms' AI engagement using 10-K filings.
problem Opaque AI selection criteria in existing ETFs.
method NLP analysis of 10-K filings to classify AI stocks.
result Companies with higher AI engagement have greater positive returns.
Benchmark evaluates AI-generated financial QA hallucinations, highlighting system vulnerabilities.
problem Ensuring factual accuracy of AI-generated financial QA outputs.
method Developed a benchmark dataset and evaluated six detection methods under clean and noisy conditions.
result LLM-based judges and embedding methods perform best, but degrade under noisy conditions.
System segments Form 10-K documents into Item sections for financial analysis.
problem Segmenting Form 10-K documents into Item sections for efficient financial analysis.
method Developed an automatic Form 10-K Itemization system using NLP techniques.
result System achieves a retrieval rate of 93% for segmenting Item sections.
Fine-grained event tagging system for SEC 8-K filings improves precision to 96%.
problem Coarse SEC item codes mislabel routine and significant events.
method Two-stage system tagging 8-K disclosures against a 119-event taxonomy.
result LLM judge finds precision rises to 96% with quality scores.
IPO Finance Agent evaluates LLMs on SpaceX IPO due diligence, surpassing Finance Agent v2.
problem Evaluating language models on financial tasks like IPO due diligence.
method Introducing IPO Finance Agent and an evaluator-optimizer pipeline.
result The best-performing model reaches 79.4% accuracy at 0.30 USD per query.
Large language models learn company embeddings from SEC filings.
problem Lack of a rigorous definition of company similarity.
method Pre-trained and finetuned large language models (LLMs) to learn embeddings from SEC filings.
result LLMs can reproduce GICS classifications and indicate similar financial performance.
The study analyzes trading imbalances from SEC Form 13F-HR filings to identify profitable trading opportunities.
problem Identifying profitable trading opportunities based on SEC Form 13F-HR filings.
method Statistical analysis of holdings variations and imbalances between consecutive reporting periods.
result A profitable trading strategy can be implemented by betting against the sign of imbalances with a 1-2 month time horizon.
Study uses LLM to extract and compare segment disclosures from financial filings.
problem Challenges in completeness and comparability of segment disclosures in financial reports.
method Developed a large language model framework to extract and preserve segment information from Form 10-K filings.
result The LLM accurately extracts segment-level information and addresses cross-period knowledge questions.
Study uses LLMs to generate investor briefs from company reports and SEC filings.
problem Improving data analysis for individual investors.
method Preprocessed data, used gpt-4o model in RAG regime, evaluated by investors.
result LLMs can generate useful investor briefs from company reports and SEC filings.
Paper reviews Viro's definition of Khovanov homology for tangles.
problem Defining Khovanov homology for unoriented framed tangles.
method Explains Viro's definition and the relation between R-matrix and Kauffman bracket. result Clarifies the relation between R-matrix and Kauffman bracket in Khovanov homology. FinBERT-XRC model assesses financial report risk, offering transparent explanations.
problem Assessing post-event return volatility risk in financial reports.
method Deep-learning model FinBERT-XRC with explainability at word, sentence, and corpus levels.
result FinBERT-XRC outperforms state-of-the-art models in predictive accuracy.
FinCARE combines financial data and AI reasoning to improve causal analysis of financial performance.
problem Correlation-based analysis fails to capture true causal relationships in financial performance.
method Hybrid framework integrating causal discovery algorithms with financial domain knowledge from SEC filings and LLM reasoning.
result KG+LLM-enhanced methods improve causal discovery across PC, GES, and NOTEARS by 36-366%.
Two new metrics assess LLM faithfulness and entropy, improving model reliability.
problem Evaluating the accuracy of LLMs in generating coherent responses.
method Proposes SF and SEP metrics based on information theory and thermodynamics.
result High SF and SEP scores indicate more faithful LLM responses.
Paper fine-tunes a language model to predict long-term stock buy signals.
problem Predicting long-term stock price movements with narrative text.
method Fine-tuning a small language model on 10-K reports for buy/sell decisions.
result Buy signals generated from 10-K text are most precise at 6 and 9 months, providing 4.8-9% improvement over random selection.
TinyXRA assesses financial risks from 10-K reports using a lightweight transformer model.
problem Comprehensive risk assessment from financial reports, distinguishing between upside and downside risk.
method Lightweight transformer model with dynamic attention, incorporating skewness, kurtosis, and Sortino ratio.
result State-of-the-art predictive accuracy and transparent risk assessments.
Study finds CNNs perform better with financial ratio data than fundamental data.
problem Improving CNN performance with financial data.
method Developed and analyzed three image encoding methods for financial data.
result Image encoding methods improve CNN performance for financial ratio data but not significantly for fundamental data.
Two methods improve 10-K item segmentation using large language models.
problem Challenges in extracting specific items from 10-K reports due to variations in document formats and item presentation.
method Two advanced item segmentation methods: GPT4ItemSeg and BERT4ItemSeg.
result BERT4ItemSeg achieves a macro-F1 of 0.9825, surpassing other methods.
New model uses financial filings to predict bankruptcy, even without MDA sections.
problem Lack of complete MDA data limits traditional bankruptcy prediction models.
method Conditional Multimodal Discriminative (CMMD) model learns from accounting, market, and textual data.
result Empirical results show superior classification performance compared to traditional models.
LLMs cause inconsistent financial outputs, smaller models are more reliable.
problem Inconsistent outputs from LLMs undermine auditability and trust in financial workflows.
method Finance-calibrated deterministic test harness, task-specific invariant checking, model classification, and cross-provider validation.
result Smaller models (Granite-3-8B, Qwen2.5-7B) achieve 100% output consistency, while larger models like GPT-OSS-120B have high drift.
Financial statements contain quantitative information and manager's subjective evaluation of firm's financial status. Using information released in U.S. 10-K filings. Both qualitative and quantitative appraisals are crucial for quality financial decisions. To extract such opinioned statements from the reports, we built…
We establish a new algebraic characterization of sectional curvature bounds sec≥k and sec≤k using only curvature terms in the Weitzenböck formulae for symmetric p-tensors. By introducing a symmetric analogue of the Kulkarni-Nomizu product, we provide a simple formula for such curvature terms. We also gi…
Deep RL model uses multimodal data for better stock portfolio optimization.
problem Optimizing trading strategies for SP100 stocks using complex data sources.
method Multimodal deep reinforcement learning with state tensors, CNNs, and RNNs.
result Agent outperforms standard benchmarks in portfolio performance.
Enhances financial analysis with multi-agent collaboration.
problem Limited use of AI-agent collaboration in financial research.
method Proposes a multi-agent system for financial investment research.
result Multi-agent system outperforms single-agent models.
Research explores how local communities and corporations interact in finance.
problem Impact of local government subsidies and corporate bankruptcy on bond yields.
method Difference-in-differences analysis, econometric models, deep-learning model.
result Corporate subsidies and bankruptcy filings affect bond yields significantly.
LLMs help less-resourced researchers access costly data.
problem Unequal access to costly datasets limits research contributions.
method RAG framework with GPT-4o-mini for automated data collection.
result LLMs can collect CEO pay ratios and CAMs from corporate disclosures with high accuracy and low cost.
The paper uses machine learning to detect malicious executable files.
problem Detecting malicious executable files using static analysis.
method Pre-processing, cleaning, encoding, feature selection, and ensemble training of classifiers.
result An ensemble of classifiers effectively detects malicious executable files.
Study shows SEC crypto classification led to significant market reactions.
problem Impact of SEC classification of crypto assets as securities.
method Event study methodology focusing on explicitly named crypto assets.
result Significant adverse market reactions, with returns plummeting 12% over one week.
Study evaluates five LLMs for financial report analysis, revealing performance differences and variability.
problem Lack of understanding in reliability, consistency, and transparency of LLMs in financial analysis.
method Human evaluation, automated similarity metrics, and behavioral diagnostics applied to five transformer-based LLMs over U.S. 10-K filings.
result No single LLM consistently dominates across all evaluation perspectives, highlighting variability and need for interpretability.
MarketSenseAI uses LLMs to improve stock analysis and outperforms benchmarks.
problem Improving accuracy in stock analysis and selection.
method Combining LLMs with SEC filings, earnings calls, and macroeconomic reports.
result Significant improvement in fundamental analysis accuracy and outperformance of benchmarks.
Flexible log file parsing using HMM adapts to evolving content.
problem Dynamic log file processing with evolving content.
method Modeling frequent patterns into HMM for flexible log file parsing.
result High accuracy (over 99%) in parsing different system log files.
Study shows fiduciary duty reduces municipal bond yields by 9% after SEC rule.
problem Effect of fiduciary duty on municipal bond yields and fees.
method Difference-in-differences analysis using hand-collected data.
result Bond yields decrease by 9% after SEC rule, but smaller issuers see increased borrowing costs.
Gradient boosting detects insider purchases predicting abnormal returns in microcap stocks.
problem Predicting abnormal returns in U.S. microcap stocks using insider purchase signals.
method Gradient boosting classifier trained on insider identity, transaction history, and market conditions.
result Gradient boosting classifier achieves AUC of 0.70 on out-of-sample data, with precision and recall of 0.38 and 0.69 respectively.
We classify four-dimensional shrinking Ricci solitons satisfying Sec≥241R, where Sec and R denote the sectional and the scalar curvature, respectively. They are isometric to either R4 (and quotients), S4, RP4 or CP2 with their standard metrics…
New rigidity results for critical metrics with curvature pinching.
problem Understanding critical metrics with curvature pinching conditions.
method Proving rigidity for metrics defined on closed smooth manifolds that are critical for a quadratic functional.
result Bach-flat metrics with constant scalar curvature satisfying Sec > 1/48 R are Einstein and isometric to specific spaces.
Holomorphic torsion invariant for log-Enriques surfaces derived from Borcherds products.
problem Holomorphic torsion invariant for log-Enriques surfaces.
method Introduced a holomorphic torsion invariant using Borcherds products.
result The invariant is given by the Petersson norm of an explicit Borcherds product.
BERTopic improves financial text analysis with FinTextSim's contextual embeddings.
problem Analyzing financial text data for insights and predictions.
method Integrates BERTopic with FinTextSim for topic modeling and clustering.
result BERTopic performs better with FinTextSim's embeddings, improving topic clarity and reducing misclassification.
We study Weil-Petersson (WP) geodesics with narrow end invariant and develop techniques to control length-functions and twist parameters along them and prescribe their itinerary in the moduli space of Riemann surfaces. This class of geodesics is rich enough to provide for examples of closed WP geodesics in the thin par…
Measuring the similarity of two files is an important task in malware analysis, with fuzzy hash functions being a popular approach. Traditional fuzzy hash functions are data agnostic: they do not learn from a particular dataset how to determine similarity; their behavior is fixed across all datasets. In this paper, we …
Model predicts trade volume changes from financial filings.
problem Improving financial market understanding through machine learning.
method Hierarchical Reformer model trained on SEDAR filings.
result Model can predict trade volume changes without explicit training.
We investigate length decreasing maps f:M→N between Riemannian manifolds M, N of dimensions m≥2 and n, respectively. Assuming that M is compact and N is complete such that $$\sec_M>-σ\quad\text{and}\quad{\Ric}_M\ge(m-1)σ\ge(m-1)\sec_N\ge-μ,$$ where σ, μ are positive constants, we show that the m…
In record linkage (RL), or exact file matching, the goal is to identify the links between entities with information on two or more files. RL is an important activity in areas including counting the population, enhancing survey frames and data, and conducting epidemiological and follow-up studies. RL is challenging when…
We consider minimal maps f:M→N between Riemannian manifolds (M,gM) and (N,gN), where M is compact and where the sectional curvatures satisfy secN≤σ≤secM for some σ>0. Under certain assumptions on the differential of the map and the second fundamental form of the graph Γ(f)…
A Lorentzian manifold is defined here as a smooth pseudo-Riemannian manifold with a metric tensor of signature ((2n +1, 1)). A Robinson manifold is a Lorentzian manifold (M) of dimension (\geqslant 4) with a subbundle (N) of the complexification of (TM) such that the fibers of (N\to M) are maximal totally null (isotrop…