LLMs are applied in a generative pipeline for extracting, normalizing, and interpreting eligibility criteria from securities prospectuses, achieving up to 91% precision in document-level decisions with a conservative bias.
hub
Finbert: A pretrained language model for financial communications
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 15roles
background 1polarities
background 1representative citing papers
StakeBench is a new benchmark using market-derived supervision from resolved prediction markets to test LLMs on commitment detection, side identification, action anticipation, and odds projection, revealing partial success on sides but structural failures on higher tasks.
Introduces FinTruthQA, a 6,000-entry annotated benchmark for AI assessment of financial disclosure quality across four criteria, with model evaluations showing strong results on question tasks but weaker on answer relevance.
FinAgent-RAG achieves 76.81-78.46% execution accuracy on financial QA benchmarks by combining contrastive retrieval, program-of-thought code generation, and adaptive strategy routing, outperforming baselines by 5.62-9.32 points.
SBCA is a reinforcement learning framework using BERT cross-modal fusion and Actor-Critic to integrate price data with sentiment text for multi-asset portfolio optimization with practical trading constraints.
CGCMA separates text-conditioned grounding from lag-aware trust gating to fuse asynchronous price and web data, yielding the highest Sharpe ratio of +0.449 on a new crypto news corpus.
FinFRE-RAG combines importance-guided feature reduction with label-aware retrieval-augmented generation to boost LLM performance on tabular fraud detection across four public datasets while providing human-readable rationales.
A clustering-based synthetic data distillation framework enables compact models to match or exceed a large teacher on financial sentiment analysis using only a small set of real labeled examples.
YouZhi-LLM applies a layer-adaptive GQA-to-MLA transition plus Ascend-specific distillation and fine-tuning to reduce KV-cache size, yielding up to 2.69× higher concurrency and modest gains on financial benchmarks versus base models.
NORA applies task-aware weighting and NPK filtering to handle label noise in multi-attribute tagging of financial numerical entities, outperforming baselines on a new 6.6M-instance benchmark.
Media sentiment indicators from Canadian news, when added to a New Keynesian model with endogenous central-bank response, improve out-of-sample forecasts and account for part of monetary-policy propagation to output and prices.
Systematic tests show that specific PDF parsers combined with overlapping chunking strategies better preserve structure and improve RAG answer correctness on financial QA benchmarks including the new TableQuest dataset.
PRAGMA pre-trains a Transformer on heterogeneous banking events with a tailored self-supervised masked objective, yielding embeddings that support strong downstream performance on credit scoring, fraud detection, and lifetime value prediction using linear heads or light fine-tuning.
A survey synthesizing recent LLM research and assessing its applicability to financial data analysis.
A literature review that categorizes bias in LLMs, surveys evaluation and mitigation techniques, and discusses ethical implications.
citing papers explorer
-
Agentic Retrieval-Augmented Generation for Financial Document Question Answering
FinAgent-RAG achieves 76.81-78.46% execution accuracy on financial QA benchmarks by combining contrastive retrieval, program-of-thought code generation, and adaptive strategy routing, outperforming baselines by 5.62-9.32 points.
-
Noise-Robust Financial Numerical Entity Attribute Tagging
NORA applies task-aware weighting and NPK filtering to handle label noise in multi-attribute tagging of financial numerical entities, outperforming baselines on a new 6.6M-instance benchmark.