SOURCE-LINKED INTELLIGENCE

When Financial Fine-tuning Fails: A Three-Level Detectability Analysis of Numerical Hallucination in Domain-Adapted Language Models

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

Financial large language models are increasingly deployed for summarization of reports and disclosures, where numerical hallucination poses significant practical risks. While prior work often attributes such hallucination to insufficient numerical reasoning, this assumption has not been systematically tested under controlled fine-tuning settings. In this paper, we conduct a cost-effective, controlled study of numerical hallucination in financial summarization across three model variants: a base instruction-tuned model, a domain language-adapted model (FT-A), and a numeracy-enhanced domain mode

Read original source ↗ Open in workspace

recordType

paper

region

Global