Explore the corpus

Find evidence, not just documents.

Search Minerva’s current Findings using transparent hybrid retrieval. Results remain strictly inside the configured corpus.

Hybrid retrieval

Results for “LLMs”

30 findings

74match

Finding 46481 source

The input text lacks substantive content, providing only a title, author details, and an incomplete sentence about a generative-AI framework for finance using LLMs to encode cross-sectional equity structure. Without further information, it is impossible to assess originality, novelty, or impact, making meaningful evaluation or engagement impossible.

LexicalMeaningQualityGraph

Matched: generative, language, large, llms, models

74match

Finding 46451 source

Researchers unveil a pioneering generative-AI framework for finance, leveraging Large Language Models (LLMs) to analyze equity markets cross-sectional structure, offering a fresh, nuanced perspective on complex financial data and stock relationships.

LexicalMeaningQualityGraph

Matched: generative, language, large, llms, models

72match

Finding 46471 source

Results reveal the framework uncovers hidden market patterns and boosts predictive accuracy, a promising trend, though the paper lacks detailed empirical results and discussion of limitations like data quality or model interpretability.

LexicalMeaningQualityGraph

Matched: generative, language, large, llms, models

69match

Finding 45291 source

Despite impressive results, the paper notes limited discussion on transparency and performance in other markets or smaller deals, raising questions about broader applicability and real-world challenges for generative AI in finance.

LexicalMeaningQualityGraph

Matched: generative, language, large, llms, models

68match

Finding 46461 source

The studys standout innovation is adapting LLMstraditionally used for textto encode intricate financial datasets, bridging machine learning and finance, and introducing new terminology that could reshape financial modeling and analysis.

LexicalMeaningQualityGraph

Matched: generative, language, large, llms, models

65match

Finding 45271 source

Large language models like OpenAI's o3, GPT-5, and GPT-5.1 can accurately predict short-term stock market reactions to major U.S. M&A announcements, outperforming traditional methods such as logistic regression.

LexicalMeaningQualityGraph

Matched: generative, language, large, llms, models

65match

Finding 54751 source

Large Language Models (LLMs) and Generative AI are revolutionizing quantitative investment research, not only automating tasks but also bridging human expertise and systematic models, ushering in Augmented Financial Intelligence (AFI).

LexicalMeaningQualityGraph

Matched: generative, language, large, llms, models

64match

Finding 46651 source

The research demonstrates that deep generative models are effective for financial applications, such as risk analysis and portfolio optimization. Future work could explore additional architectures and features. Potential applications include creating optimal portfolios and improving risk management strategies.

LexicalMeaningQualityGraph

Matched: generative, language, large, models

63match

Finding 45281 source

The study shows reasoning-based LLMs interpret complex deal, company, and economic data from 2012-2022, enabling investment portfolios with higher risk-adjusted returns and signaling a major shift in financial decision-making.

LexicalMeaningQualityGraph

Matched: generative, language, large, llms, models

63match

Finding 38251 source

The study concludes that the proposed framework significantly enhances financial sentiment analysis accuracy. Potential applications include improved market movement forecasting and investment decision-making. Future research could integrate macroeconomic and microeconomic data for even more precise predictions.

LexicalMeaningQualityGraph

Matched: language, large, llms, models

63match

Finding 53431 source

The SEP framework enhances explainable stock predictions and portfolio construction, with potential applications in financial analysis and investment strategies. Future research could focus on increasing robustness and incorporating additional data sources. The study's limitations include potential cumulative errors in the SEP process.

LexicalMeaningQualityGraph

Matched: generative, language, large, llms, models

63match

Finding 42841 source

The research suggests that FinPT can significantly enhance financial risk prediction, with potential applications in default, fraud, and churn prediction. Future research could explore other tuning strategies and expand the benchmark. The study highlights the importance of unified benchmarks and advanced models in financial risk prediction.

LexicalMeaningQualityGraph

Matched: generative, language, large, llms, models

63match

Finding 52711 source

The study introduces a hybrid approach combining static classification with generative techniques, utilizing transformer models and self-attention on earnings transcripts and social media, advancing quantitative finance despite market language challenges.

LexicalMeaningQualityGraph

Matched: generative, language, large, llms, models

62match

Finding 85881 source

The research underscores ChatGPT's potential in financial NLP tasks despite its limitations. Future work should address contamination issues and labeling time challenges. Potential applications include financial sentiment analysis, numerical claim detection, and named entity recognition in financial texts.

LexicalMeaningQualityGraph

Matched: generative, language, large, llms, models

62match

Finding 45301 source

This paper uniquely applies state-of-the-art LLMs (OpenAIs o3, GPT-5, GPT-5.1) to M& A announcement return prediction, surpassing traditional logistic regression and naive benchmarks in both predictive accuracy and portfolio performance. Its reasoning-based approach to M& A events offers compelling innovation, practical relevance, and significant impact for empirical finance and investment management.

LexicalMeaningQualityGraph

Matched: generative, language, large, llms, models

62match

Finding 83501 source

The research demonstrates that language-specific pre-training can significantly enhance the performance of LLMs in extracting sentiment factors from Chinese financial news. This has potential applications in developing more effective quantitative trading strategies. Future research could explore further fine-tuning and pre-training techniques.

LexicalMeaningQualityGraph

Matched: language, large, llms, models

62match

Finding 41791 source

Groundbreaking research reveals that large language models (LLMs) in finance make more rational, information-driven trading decisions than humans, avoiding herd behavior that often triggers asset bubbles and financial crises.

LexicalMeaningQualityGraph

Matched: generative, language, large, llms, models

62match

Finding 50561 source

The research shows that instruction tuning LLMs can significantly enhance financial sentiment analysis. Potential applications include improved market prediction tools and financial news analysis. Future research could explore broader financial tasks and further refine instruction tuning methods.

LexicalMeaningQualityGraph

Matched: language, large, llms, models

61match

Finding 42461 source

FinLBench debuts as a pioneering benchmark for testing large language models ability to analyze long Chinese financial documents, featuring the meticulously annotated FinLEval dataset with 3,219 question-answer pairs across six document types.

LexicalMeaningQualityGraph

Matched: language, large, llms, models

61match

Finding 68521 source

A study integrates advanced generative AI in risk management by fine-tuning language models to improve credit assessments, market forecasts, and anomaly detection, yielding 70% accurate questions and 60% correct classifications.

LexicalMeaningQualityGraph

Matched: generative, language, large, llms, models

60match

Finding 70561 source

The research demonstrates the effectiveness of LLMs in predicting stock returns and developing investment strategies. Potential applications include enhancing market prediction and investment decision-making methodologies, with implications for asset managers, institutional investors, and financial regulators.

LexicalMeaningQualityGraph

Matched: language, large, llms, models

60match

Finding 57461 source

Researchers used advanced multilingual models and a novel sentence-level alignment method to separate shared and language-specific news. Inefficiencies are strongest in smaller, domestically owned firms and when readership is low.

LexicalMeaningQualityGraph

Matched: language, large, llms, models

60match

Finding 42471 source

Commercial LLMs consistently outperform open-source models on FinLBench tasks, but all models struggle with hallucinationfabricating information, especially when confronted with trap questions, exposing a critical and surprising weakness in current AI systems.

LexicalMeaningQualityGraph

Matched: language, large, llms, models

60match

Finding 57641 source

Researchers show that merging large language models (LLMs) pre-trained on different skillslike finance, math, and Japanesecreates powerful, multi-skilled models, with surprising cross-lingual benefits and improved reasoning on complex financial tasks.

LexicalMeaningQualityGraph

Matched: generative, language, large, llms, models

60match

Finding 57471 source

This paper uniquely investigates how multilingual LLMs reveal inefficiencies in price discovery caused by language segmentation in global news. Employing advanced NLP methods like multilingual sentence embeddings and optimal transport, it empirically demonstrates language-induced return predictability, offering novel insights with significant implications for AI-driven trading, international finance, and market efficiency.

LexicalMeaningQualityGraph

Matched: language, large, llms, models

60match

Finding 52671 source

This paper innovatively fuses large language models with equity market analysis, synthesizing and categorizing research trends into a dual framework. Its novelty lies in bridging AI with quantitative finance, offering fresh perspectives for professionals despite its review nature. The work remains engaging, relevant, and valuable for practitioners seeking market insights.

LexicalMeaningQualityGraph

Matched: language, large, llms, models

60match

Finding 42481 source

The studys rigorous manual annotation and focus on long-text financial analysis mark a significant advance, though future work should include more diverse documents and address hallucination to further strengthen AI reliability in finance.

LexicalMeaningQualityGraph

Matched: language, large, llms, models

59match

Finding 42511 source

FinLLM-B, a dedicated large language model, revolutionizes financial breakout trading detection by outperforming GPT-3.5 and GPT-4 nearly 50% in average accuracy and 57% in perfection rate with exceptional breakthrough performance.

LexicalMeaningQualityGraph

Matched: language, large, llms, models

59match

Finding 57441 source

Language barriers slow financial market reactions to global news, even when content is nearly identical. Investors in Japan and the U.S. do not fully combine information from both Japanese and English sources.

LexicalMeaningQualityGraph

Matched: language, large, llms, models

59match

Finding 27881 source

Researchers showed that large language models can autonomously generate and test asset pricing hypotheses, proposing 280 investment signals, with 38 demonstrating unique predictive power after rigorous comparison against 209 known financial anomalies.

LexicalMeaningQualityGraph

Matched: language, large, llms, models