Agentic Retrieval of Topics and Insights from Earnings Calls
This addresses the need for financial analysts to track evolving company strategies, though it is incremental as it builds on existing topic modeling techniques.
The authors tackled the problem of dynamically capturing emerging topics in earnings calls, proposing an LLM-agent approach that extracts and structures topics into a hierarchical ontology, resulting in improved ontology coherence and topic evolution accuracy.
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.