Research map / Large language models / Language, safety and interpretability

HaDeMiF: Hallucination Detection and Mitigation in Large Language Models

ICLR 2025 · Large language models › Language, safety and interpretability · approach: Data and hallucination detection

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a conceptual operational framework for LLM hallucination management, combining root-cause-aware detection (uncertainty, consistency, fact-checking) and stratified mitigation in a closed improvement loop, illustrated with a financial data extraction case study.

Problem

Hallucinations in LLMs and LRMs pose reliability risks in high-stakes domains such as finance and law, and current detection and mitigation methods are fragmented and lack root-cause awareness.

Approach

Organizes hallucination detection and mitigation around a root-cause taxonomy (model, data, context) inside a continuous improvement cycle (detection, mitigation, validation, refinement), with a tiered architecture for a financial data extraction use case.

Key results

• No quantitative experimental results are reported; the case study is described illustratively without measured outcomes.

Limitations

• No empirical evaluation of the framework or case study results are provided
• Framework is largely descriptive with many citations marked as placeholders

Experimental setup

Builds on: semantic entropy temperature scaling self-consistency prompting chain-of-thought prompting retrieval-augmented generation

Closest papers by meaning

• LLM-Check: Investigating Detection of Hallucinations in Large Language Models (NeurIPS 2024 · similarity 0.95)
• Scalable Token-Level Hallucination Detection in Large Language Models (NeurIPS 2026 · similarity 0.95)
• Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback (AAAI 2025 · similarity 0.93)
• ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models (NeurIPS 2024 · similarity 0.93)
• Attributive Reasoning for Hallucination Diagnosis of Large Language Models (AAAI 2025 · similarity 0.93)
• Robust Hallucination Detection in LLMs via Adaptive Token Selection (NeurIPS 2025 · similarity 0.92)