[LLM] LLM for Financial Research Paper List: Read and To-Read
Large Language Model Agent in Financial Trading: A Survey
Large Language Model Agent in Financial Trading: A Survey
Trading is a highly competitive task that requires a combination of strategy, knowledge, and psychological fortitude. With the recent success of large language models(LLMs), it is appealing to apply the emerging intell…
ar5iv.labs.arxiv.org
A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist (FinAgent)
A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist
Financial trading is a crucial component of the markets, informed by a multimodal information landscape encompassing news, prices, and Kline charts, and encompasses diverse tasks such as quantitative trading and high-f…
ar5iv.labs.arxiv.org
Can GPTmodels be Financial Analysts? AnEvaluation of ChatGPT and GPT-4 on mock CFA Exams
Can GPT models be Financial Analysts? An Evaluation of ChatGPT and GPT-4 on mock CFA Exams
Large Language Models (LLMs) have demonstrated remarkable performance on a wide range of Natural Language Processing (NLP) tasks, often matching or even beating state-of-the-art task-specific models. This study aims at…
ar5iv.labs.arxiv.org
FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets
FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets
In the swiftly expanding domain of Natural Language Processing (NLP), the potential of GPT-based models for the financial sector is increasingly evident. However, the integration of these models with financial datasets…
ar5iv.labs.arxiv.org
FinGPT라는 오픈소스 LLM을 금융 데이터셋에 맞춰 학습하고 평가하는 과정을 다룸
- Instruction Tuning으로 금융 분야에 특화된 LLM을 효율적으로 학습시킴
- 다양한 금융 관련 task(NER, 감성 분석, 헤드라인 분류, 관계 추출 등) 성능 평가
- 이전에 보지 못한 task에 대한 제로샷 성능 평가
Beyond Classification: Financial Reasoningin State-of-the-Art Language Models
Beyond Classification: Financial Reasoning in State-of-the-Art Language Models
Large Language Models (LLMs), consisting of 100 billion or more parameters, have demonstrated remarkable ability in complex multi-step reasoning tasks. However, the application of such generic advancements has been lim…
ar5iv.labs.arxiv.org
LLM이 금융 추론을 처리할 수 있는지를 탐구
- 다양한 매개변수 크기의 GPT 모델들(2.8B~13B)을 평가
- 6B 이상의 모델에서 일관된 금융 추론 능력이 발현됨을 발견
- Instruction Tuning과 데이터셋 크기가 성능 향상에 중요한 역할을 함
- sFIOG(Synthetic-Financial Investment Opinion Generation)를 제공
- 11,802개의 인공 투자 의견 데이터를 포함한 공개 데이터셋