FISHNET: Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert Swarms, and Task Planning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929558742106112 |
|---|---|
| author | Cho, Nicole Srishankar, Nishan Cecchi, Lucas Watson, William |
| author_facet | Cho, Nicole Srishankar, Nishan Cecchi, Lucas Watson, William |
| contents | Financial intelligence generation from vast data sources has typically relied on traditional methods of knowledge-graph construction or database engineering. Recently, fine-tuned financial domain-specific Large Language Models (LLMs), have emerged. While these advancements are promising, limitations such as high inference costs, hallucinations, and the complexity of concurrently analyzing high-dimensional financial data, emerge. This motivates our invention FISHNET (Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert swarming, and Task planning), an agentic architecture that accomplishes highly complex analytical tasks for more than 98,000 regulatory filings that vary immensely in terms of semantics, data hierarchy, or format. FISHNET shows remarkable performance for financial insight generation (61.8% success rate over 5.0% Routing, 45.6% RAG R-Precision). We conduct rigorous ablations to empirically prove the success of FISHNET, each agent's importance, and the optimized performance of assembling all agents. Our modular architecture can be leveraged for a myriad of use-cases, enabling scalability, flexibility, and data integrity that are critical for financial tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_19727 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FISHNET: Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert Swarms, and Task Planning Cho, Nicole Srishankar, Nishan Cecchi, Lucas Watson, William Artificial Intelligence Computation and Language Information Retrieval Machine Learning Financial intelligence generation from vast data sources has typically relied on traditional methods of knowledge-graph construction or database engineering. Recently, fine-tuned financial domain-specific Large Language Models (LLMs), have emerged. While these advancements are promising, limitations such as high inference costs, hallucinations, and the complexity of concurrently analyzing high-dimensional financial data, emerge. This motivates our invention FISHNET (Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert swarming, and Task planning), an agentic architecture that accomplishes highly complex analytical tasks for more than 98,000 regulatory filings that vary immensely in terms of semantics, data hierarchy, or format. FISHNET shows remarkable performance for financial insight generation (61.8% success rate over 5.0% Routing, 45.6% RAG R-Precision). We conduct rigorous ablations to empirically prove the success of FISHNET, each agent's importance, and the optimized performance of assembling all agents. Our modular architecture can be leveraged for a myriad of use-cases, enabling scalability, flexibility, and data integrity that are critical for financial tasks. |
| title | FISHNET: Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert Swarms, and Task Planning |
| topic | Artificial Intelligence Computation and Language Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2410.19727 |