Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.07906 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913936672030720 |
|---|---|
| author | Gupta, Anant Bhowmik, Rajarshi Gunow, Geoffrey |
| author_facet | Gupta, Anant Bhowmik, Rajarshi Gunow, Geoffrey |
| contents | Tracking the strategic focus of companies through topics in their earnings calls is a key task in financial analysis. However, as industries evolve, traditional topic modeling techniques struggle to dynamically capture emerging topics and their relationships. In this work, we propose an LLM-agent driven approach to discover and retrieve emerging topics from quarterly earnings calls. We propose an LLM-agent to extract topics from documents, structure them into a hierarchical ontology, and establish relationships between new and existing topics through a topic ontology. We demonstrate the use of extracted topics to infer company-level insights and emerging trends over time. We evaluate our approach by measuring ontology coherence, topic evolution accuracy, and its ability to surface emerging financial trends. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_07906 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Agentic Retrieval of Topics and Insights from Earnings Calls Gupta, Anant Bhowmik, Rajarshi Gunow, Geoffrey Machine Learning Artificial Intelligence Tracking the strategic focus of companies through topics in their earnings calls is a key task in financial analysis. However, as industries evolve, traditional topic modeling techniques struggle to dynamically capture emerging topics and their relationships. In this work, we propose an LLM-agent driven approach to discover and retrieve emerging topics from quarterly earnings calls. We propose an LLM-agent to extract topics from documents, structure them into a hierarchical ontology, and establish relationships between new and existing topics through a topic ontology. We demonstrate the use of extracted topics to infer company-level insights and emerging trends over time. We evaluate our approach by measuring ontology coherence, topic evolution accuracy, and its ability to surface emerging financial trends. |
| title | Agentic Retrieval of Topics and Insights from Earnings Calls |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.07906 |