Agentic Retrieval of Topics and Insights from Earnings Calls

TL;DR

This paper introduces an LLM-agent driven method to dynamically extract, structure, and analyze emerging topics from earnings calls, enabling better tracking of company strategies and financial trends over time.

Contribution

It presents a novel LLM-based framework for hierarchical topic extraction and evolution tracking in financial documents, improving upon traditional static models.

Findings

High ontology coherence achieved

Accurate detection of emerging topics

Effective inference of company insights

Abstract

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.