Enregistré dans:
Détails bibliographiques
Auteurs principaux: Pesaranghader, Ahmad, Li, Erin
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2601.09929
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911377033003008
author Pesaranghader, Ahmad
Li, Erin
author_facet Pesaranghader, Ahmad
Li, Erin
contents Large Language Models (LLMs) and Large Reasoning Models (LRMs) offer transformative potential for high-stakes domains like finance and law, but their tendency to hallucinate, generating factually incorrect or unsupported content, poses a critical reliability risk. This paper introduces a comprehensive operational framework for hallucination management, built on a continuous improvement cycle driven by root cause awareness. We categorize hallucination sources into model, data, and context-related factors, allowing targeted interventions over generic fixes. The framework integrates multi-faceted detection methods (e.g., uncertainty estimation, reasoning consistency) with stratified mitigation strategies (e.g., knowledge grounding, confidence calibration). We demonstrate its application through a tiered architecture and a financial data extraction case study, where model, context, and data tiers form a closed feedback loop for progressive reliability enhancement. This approach provides a systematic, scalable methodology for building trustworthy generative AI systems in regulated environments.
format Preprint
id arxiv_https___arxiv_org_abs_2601_09929
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hallucination Detection and Mitigation in Large Language Models
Pesaranghader, Ahmad
Li, Erin
Artificial Intelligence
Large Language Models (LLMs) and Large Reasoning Models (LRMs) offer transformative potential for high-stakes domains like finance and law, but their tendency to hallucinate, generating factually incorrect or unsupported content, poses a critical reliability risk. This paper introduces a comprehensive operational framework for hallucination management, built on a continuous improvement cycle driven by root cause awareness. We categorize hallucination sources into model, data, and context-related factors, allowing targeted interventions over generic fixes. The framework integrates multi-faceted detection methods (e.g., uncertainty estimation, reasoning consistency) with stratified mitigation strategies (e.g., knowledge grounding, confidence calibration). We demonstrate its application through a tiered architecture and a financial data extraction case study, where model, context, and data tiers form a closed feedback loop for progressive reliability enhancement. This approach provides a systematic, scalable methodology for building trustworthy generative AI systems in regulated environments.
title Hallucination Detection and Mitigation in Large Language Models
topic Artificial Intelligence
url https://arxiv.org/abs/2601.09929