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

תקציר מקורי באנגליתarXiv:2609.04806v1 Announce Type: new Abstract: 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 model (FT-A+B+C). We introduce a three-level detectability taxonomy distinguishing between overt hallucination (currency-denominated fabrication), covert-ex