# LLM-based Triplet Extraction from Financial Reports

arXiv: https://arxiv.org/abs/2602.11886 · HTML: https://mlsanity.com/paper/2602.11886/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 12 Feb 2026.

## Builds on (most cited first, 8 of 8)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [DocRED: A Large-Scale Document-Level Relation Extraction Dataset](https://mlsanity.com/paper/1906.06127/) (2019)
- [Text2KGBench: A Benchmark for Ontology-Driven Knowledge Graph Generation from Text](https://mlsanity.com/paper/2308.02357/) (2023)
- [Developing a Scalable Benchmark for Assessing Large Language Models in Knowledge Graph Engineering](https://mlsanity.com/paper/2308.16622/) (2023)
- [Zero- and Few-Shots Knowledge Graph Triplet Extraction with Large Language Models](https://mlsanity.com/paper/2312.01954/) (2023)

## Abstract (arXiv)

Corporate financial reports are a valuable source of structured knowledge for Knowledge Graph construction, but the lack of annotated ground truth in this domain makes evaluation difficult. We present a semi-automated pipeline for Subject-Predicate-Object triplet extraction that uses ontology-driven proxy metrics, specifically Ontology Conformance and Faithfulness, instead of ground-truth-based evaluation. We compare a static, manually engineered ontology against a fully automated, document-specific ontology induction approach across different LLMs and two corporate annual reports. The automatically induced ontology achieves 100% schema conformance in all configurations, eliminating the ontology drift observed with the manual approach. We also propose a hybrid verification strategy that combines regex matching with an LLM-as-a-judge check, reducing apparent subject hallucination rates from 65.2% to 1.6% by filtering false positives caused by coreference resolution. Finally, we identify a systematic asymmetry between subject and object hallucinations, which we attribute to passive constructions and omitted agents in financial prose.