Only two of seven LLMs produce positive returns on live Polymarket data, with MiMo-V2-Flash at 17.6% CWR and Gemini-3-Flash at 6.2% CWR while the other five lose money.
hub Mixed citations
FinBERT: Financial Sentiment Analysis with Pre-trained Language Models
Mixed citation behavior. Most common role is background (56%).
45
Pith papers citing it
Background
56% of classified citations
abstract
Financial sentiment analysis is a challenging task due to the specialized language and lack of labeled data in that domain. General-purpose models are not effective enough because of the specialized language used in a financial context. We hypothesize that pre-trained language models can help with this problem because they require fewer labeled examples and they can be further trained on domain-specific corpora. We introduce FinBERT, a language model based on BERT, to tackle NLP tasks in the financial domain. Our results show improvement in every measured metric on current state-of-the-art results for two financial sentiment analysis datasets. We find that even with a smaller training set and fine-tuning only a part of the model, FinBERT outperforms state-of-the-art machine learning methods.
hub tools
citation-role summary
background 6
baseline 1
method 1
other 1
citation-polarity summary
representative citing papers
Network-augmented FinBERT embeddings from 10-K MD&A sections predict cross-sectional returns with a long-short alpha of 7.27% after standard controls.
Composite LLM scoring saturates on expert investment frameworks while Gate Reconstruction Accuracy still reveals a clear procedural deficit at the frontier.
MacroLens is a point-in-time multi-signal benchmark dataset and seven tasks for evaluating contextual financial reasoning models under macroeconomic scenarios.
VertMark embeds robust, training-free watermarks into vertical domain language models by creating hidden semantic equivalence between low-frequency triggers and high-frequency domain terms via parameter swaps, supporting reliable verification with negligible performance impact.
AgentPulse is a continuous multi-signal framework that scores AI agents on benchmark performance, adoption, sentiment and ecosystem health, showing these factors are complementary and that benchmark-plus-sentiment predicts external adoption metrics.
Single-agent systems with tools provide the optimal performance-efficiency trade-off for small language models, outperforming base models and multi-agent setups.
FinTagging decomposes XBRL tagging into FinNI extraction and FinCL full-taxonomy linking, showing LLMs handle extraction but struggle with fine-grained concept alignment in zero-shot settings.
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.
Schema-constrained, quote-grounded LLM extraction plus a second-pass quality score yields 601k auditable 8-K event tags whose precision and market reactions both improve with the score.
CLExEval introduces a human-annotated evaluation framework on 40 rare cases that identifies verbosity bias, hidden knowledge paradox, and 68.6% reasoning-to-output mismatch in LLMs while showing LLM-as-a-Judge overestimates reliability.
A continuous local model shows semantic attackability governed by the largest generalized eigenvalue of Jacobians from proxy and target embeddings, yielding closed-form flip conditions and VC-style certificates.
IPO-Mine releases a toolkit and large multimodal dataset for structured analysis of IPO filings and shows state-of-the-art models diverge from human judgments on chart quality and misleadingness.
Temporal reasoning is not the core bottleneck for LLMs on time-based QA; the real issue is unstructured text-to-event mapping, addressed by a neuro-symbolic system with PIS that reaches 100% accuracy on benchmarks when representations are correct.
Encoder models trained on SEC filings struggle with earnings calls due to domain shift, while LLMs enable open-ended KPI extraction with 79.7% human-verified precision on newly introduced benchmarks.
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.
SysTradeBench evaluates 17 LLMs on 12 trading strategies, finding over 91.7% code validity but rapid convergence in iterative fixes and a continued need for human oversight on critical strategies.
PolySwarm aggregates predictions from 50 LLM personas for Polymarket trading using Bayesian combination and divergence metrics, outperforming single models in calibration while adding latency arbitrage via CEX price models.
AutoDAN automatically generates semantically meaningful jailbreak prompts for aligned LLMs via a hierarchical genetic algorithm, achieving higher attack success, cross-model transferability, and universality than baselines while bypassing perplexity defenses.
BloombergGPT is a 50B parameter LLM trained on a 708B token mixed financial and general dataset that outperforms prior models on financial benchmarks while preserving general LLM performance.
Domain adaptation on frozen PLM embeddings helps small general backbones transfer to a restricted financial subset but gives negligible SST-2 gains and can degrade FinBERT under adversarial alignment.
PTMC is a proposed Monte Carlo estimator that generates market-outcome distributions by simulating continuous double-auction interactions among persona-conditioned neural-policy bots whose heterogeneity is drawn from a learned distribution.
An LLM-driven evolutionary framework generates executable trading strategies as Python code and uses a meta-loop to evolve the prompts that guide synthesis.
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.
citing papers explorer
-
PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Data
Only two of seven LLMs produce positive returns on live Polymarket data, with MiMo-V2-Flash at 17.6% CWR and Gemini-3-Flash at 6.2% CWR while the other five lose money.
-
Supply Chain Propagation of Textual Signals: LLM Embeddings and Cross-Sectional Return Predictability
Network-augmented FinBERT embeddings from 10-K MD&A sections predict cross-sectional returns with a long-short alpha of 7.27% after standard controls.
-
InvestPhilBench: A Multi-Layer Benchmark for Evaluating Large Language Model Procedural Reasoning in Expert Investment Philosophy
Composite LLM scoring saturates on expert investment frameworks while Gate Reconstruction Accuracy still reveals a clear procedural deficit at the frontier.
-
MacroLens: A Multi-Task Benchmark for Contextual Financial Reasoning under Macroeconomic Scenarios
MacroLens is a point-in-time multi-signal benchmark dataset and seven tasks for evaluating contextual financial reasoning models under macroeconomic scenarios.
-
VertMark: A Unified Training-Free Robust Watermarking Framework for Vertical Domain Pre-trained Language Models
VertMark embeds robust, training-free watermarks into vertical domain language models by creating hidden semantic equivalence between low-frequency triggers and high-frequency domain terms via parameter swaps, supporting reliable verification with negligible performance impact.
-
AgentPulse: A Continuous Multi-Signal Framework for Evaluating AI Agents in Deployment
AgentPulse is a continuous multi-signal framework that scores AI agents on benchmark performance, adoption, sentiment and ecosystem health, showing these factors are complementary and that benchmark-plus-sentiment predicts external adoption metrics.
-
Rethinking Scale: Deployment Trade-offs of Small Language Models under Agent Paradigms
Single-agent systems with tools provide the optimal performance-efficiency trade-off for small language models, outperforming base models and multi-agent setups.
-
FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information
FinTagging decomposes XBRL tagging into FinNI extraction and FinCL full-taxonomy linking, showing LLMs handle extraction but struggle with fine-grained concept alignment in zero-shot settings.
-
FinTruthQA: A Benchmark for AI-Driven Financial Disclosure Quality Assessment in Investor -- Firm Interactions
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.
-
Grounded Event Extraction from SEC 8-K Filings with a Fine-Grained Taxonomy
Schema-constrained, quote-grounded LLM extraction plus a second-pass quality score yields 601k auditable 8-K event tags whose precision and market reactions both improve with the score.
-
CLExEval: A Human-in-the-Loop Framework for Qualitative Evaluation of LLM Clinical Reasoning
CLExEval introduces a human-annotated evaluation framework on 40 rare cases that identifies verbosity bias, hidden knowledge paradox, and 68.6% reasoning-to-output mismatch in LLMs while showing LLM-as-a-Judge overestimates reliability.
-
Generalised Eigenvalue Geometry of Semantic Adversarial Attacks
A continuous local model shows semantic attackability governed by the largest generalized eigenvalue of Jacobians from proxy and target embeddings, yielding closed-form flip conditions and VC-style certificates.
-
IPO-Mine: A Toolkit and Dataset for Section-Structured Analysis of Long, Multimodal IPO Documents
IPO-Mine releases a toolkit and large multimodal dataset for structured analysis of IPO filings and shows state-of-the-art models diverge from human judgments on chart quality and misleadingness.
-
Temporal Reasoning Is Not the Bottleneck: A Probabilistic Inconsistency Framework for Neuro-Symbolic QA
Temporal reasoning is not the core bottleneck for LLMs on time-based QA; the real issue is unstructured text-to-event mapping, addressed by a neuro-symbolic system with PIS that reaches 100% accuracy on benchmarks when representations are correct.
-
Effective Performance Measurement: Challenges and Opportunities in KPI Extraction from Earnings Calls
Encoder models trained on SEC filings struggle with earnings calls due to domain shift, while LLMs enable open-ended KPI extraction with 79.7% human-verified precision on newly introduced benchmarks.
-
SBCA: Cross-Modal BERT-driven Actor-Critic for Multi-Asset Portfolio Optimization
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.
-
SysTradeBench: An Iterative Build-Test-Patch Benchmark for Strategy-to-Code Trading Systems with Drift-Aware Diagnostics
SysTradeBench evaluates 17 LLMs on 12 trading strategies, finding over 91.7% code validity but rapid convergence in iterative fixes and a continued need for human oversight on critical strategies.
-
PolySwarm: A Multi-Agent Large Language Model Framework for Prediction Market Trading and Latency Arbitrage
PolySwarm aggregates predictions from 50 LLM personas for Polymarket trading using Bayesian combination and divergence metrics, outperforming single models in calibration while adding latency arbitrage via CEX price models.
-
AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
AutoDAN automatically generates semantically meaningful jailbreak prompts for aligned LLMs via a hierarchical genetic algorithm, achieving higher attack success, cross-model transferability, and universality than baselines while bypassing perplexity defenses.
-
BloombergGPT: A Large Language Model for Finance
BloombergGPT is a 50B parameter LLM trained on a 708B token mixed financial and general dataset that outperforms prior models on financial benchmarks while preserving general LLM performance.
-
Is Domain Adaptation Always Helpful? A Frozen-Backbone Study of Cross-Domain Sentiment Transfer
Domain adaptation on frozen PLM embeddings helps small general backbones transfer to a restricted financial subset but gives negligible SST-2 gains and can degrade FinBERT under adversarial alignment.
-
Persona-Trained Monte Carlo: Estimating Market-Outcome Distributions via Swarms of Persona-Conditioned Neural Policy Bots in a Limit Order Book
PTMC is a proposed Monte Carlo estimator that generates market-outcome distributions by simulating continuous double-auction interactions among persona-conditioned neural-policy bots whose heterogeneity is drawn from a learned distribution.
-
AlgoEvolve: LLM-driven Meta-evolution of Algorithmic Trading Programs
An LLM-driven evolutionary framework generates executable trading strategies as Python code and uses a meta-loop to evolve the prompts that guide synthesis.
-
Efficient Financial Language Understanding via Distillation with Synthetic Data
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.
-
Can News Predict the Market? Limits of Zero-Shot Financial NLP and the Role of Explainable AI
Zero-shot NLP models do not outperform baselines for short-term stock prediction from news, but multi-layered explainability reliably separates trustworthy from unreliable outputs.
-
ACIL: Auto Chain of Thoughts for In-Context Learning
Auto-CoT automatically generates and filters reasoning-enhanced demonstrations to improve in-context learning accuracy on complex reasoning tasks.
-
Agentic Retrieval-Augmented Generation for Financial Document Question Answering
An agentic RAG system with a finance-tuned retriever, Program-of-Thought code execution, and adaptive routing reports 5.6–9.3 point gains on FinQA, ConvFinQA, and TAT-QA while cutting API cost ~41%.
-
Learning to Trade Like an Expert: Cognitive Fine-Tuning for Stable Financial Reasoning in Language Models
A new fine-tuning framework with textbook-derived MCQs and simulation-based testing enables smaller open LLMs to show competitive, risk-aware financial trading behavior that outperforms baselines.
-
Empirical Evaluation of PDF Parsing and Chunking for Financial Question Answering with RAG
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.
-
MulFSA: Multi-level Financial Sentiment Analysis Framework for Bond Market
MulFSA combines micro-level firm sentiment, meso-level industry sentiment, and duration-aware smoothing from PLMs/LLMs to extract a daily sentiment index that reduces credit spread forecast errors by 10.25% MAE and 11.94% MAPE on a 1.35M-text Chinese bond corpus.
-
Shapley in Context: Explaining Financial Language with Domain Expertise
Shapley values for LLM explanations in financial text are shown via theory and experiments to produce attributions consistent with financial reasoning.
-
Hybrid News Sentiment Engine: Real-Time Market Analysis via Adaptive Ensemble Learning on News-Price Pairs
A three-component ensemble of lexicon scoring, adaptive TF-IDF price-reaction clusters, and historical-correlation weighting generates real-time market sentiment from news-price pairs on CPU hardware.
-
MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration
MimirRAG, a multi-agent RAG framework with metadata integration and table-aware chunking, reaches 89.3% accuracy on FinanceBench and outperforms prior baselines for financial document retrieval.
-
Distribution-Free Uncertainty Quantification for Continuous AI Agent Evaluation
Adapts conformal prediction methods to provide distribution-free uncertainty quantification and coverage guarantees for continuous evaluation of AI agent quality scores.
-
Persistent and Conversational Multi-Method Explainability for Trustworthy Financial AI
An architecture stores XAI explanations persistently in searchable storage and uses RAG to synthesize multiple methods conversationally, cutting hallucination rates by 36% in a FinBERT financial sentiment demo.
-
Adaptive Financial Transformer with Regime-Gated Attention for Stock Return Prediction
Proposes Adaptive Financial Transformer with regime-gated attention and a composite loss to predict stock returns while claiming to fix backtesting issues and reduce complexity by 15.2%.
-
Transformer Scalability Crisis: The First Comprehensive Empirical Analysis of Performance Walls in Modern Language Models
Empirical tests on 118 transformers show success falling from 88.1% at 512 tokens to 0% at 2048 tokens, with compressed models achieving 649.2 tokens/sec/M parameters versus 12.5 for large generative ones.
-
The Acoustic Camouflage Phenomenon: Re-evaluating Speech Features for Financial Risk Prediction
Acoustic features degrade NLP performance in predicting stock volatility from earnings calls, attributed to 'Acoustic Camouflage' from media-trained vocal regulation.
-
A Review of Large Language Models for Stock Price Forecasting from a Hedge-Fund Perspective
This review synthesizes LLM uses in stock forecasting and catalogs key practical pitfalls from a hedge-fund viewpoint.
-
Developing an ESG-Oriented Large Language Model through ESG Practices
ESG-adapted versions of Qwen-3-4B using LoRA and IRM outperform the base model and Llama-3/Gemma-3 baselines on generative ESG question-answering tasks.
-
Transformer-Based Language Models Across Domain Verticals: Architectures, Applications and Critical Assessment
A survey paper that taxonomizes transformer architectures, reviews domain applications, and critically assesses deployment trade-offs including parameter-energy costs and alignment issues.
-
A Unified Multi-Modal Framework for Intelligent Financial Systems: Integrating Reinforcement Learning, High-Frequency Trading, and Game-Theoretic Approaches with Cross-Modal Sentiment Analysis
Proposes a unified framework merging PPO, time-series forecasting, in-context learning, game theory, and cross-modal embeddings for financial tasks and reports percentage gains over single-domain baselines.
-
Comparative Evaluation of Embedding Representations for Financial News Sentiment Analysis
On 349 financial headlines, embedding-based gradient boosting models overfit small validation sets and underperform trivial baselines, showing that embedding quality alone cannot solve low-data sentiment classification.
-
Bridging Language Models and Financial Analysis
A survey synthesizing recent LLM research and assessing its applicability to financial data analysis.
- FinEvolveBench: A Benchmark for Self-Evolving Agents on Low-Repetition Tasks with Implicit Rewards