← heapsort
RESEARCH27

Improving the Completeness and Comparability of Segment Disclosures: A Large Language Model Approach

arXiv CS.CLΒ·May 26, 2026

This study introduces a large language model-based framework to extract and preserve both reportable and nested segment disclosures directly from Form 10-K filings. It also incorporates a retrieval-augmented system to enhance comparability across multiple filings.

Read original β†—