Counterfactual Probing for Hallucination Detection and Mitigation in Large Language Models

2025/08/03 by Yijun Feng, Feng, Yijun · 1 citation
Computer Science · Social Sciences · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Misinformation and Its Impacts #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2508.01862

openalex publication_date 2025/08/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Large Language Models have demonstrated remarkable capabilities across diverse tasks, yet they frequently generate hallucinations outputs that are fluent but factually incorrect or unsupported. We propose Counterfactual Probing, a novel approach for detecting and mitigating hallucinations in LLM outputs. Our method dynamically generates counterfactual statements that appear plausible but contain subtle factual errors, then evaluates the model's sensitivity to these perturbations. We hypothesize that genuine knowledge exhibits robustness to counterfactual variations, while hallucinated content shows inconsistent confidence patterns when confronted with plausible alternatives. Our comprehensive evaluation on TruthfulQA, factual statement datasets, and curated hallucination examples demonstrates that counterfactual probing achieves superior detection performance compared to baseline methods, while our adaptive mitigation strategies reduce hallucination scores by an average of 24.5%. The approach requires no model retraining and can be integrated into existing LLM pipelines as a realtime verification mechanism.

Citations

• A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
• A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation
• Inverse Scaling: When Bigger Isn't Better
• Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback
• LM vs LM: Detecting Factual Errors via Cross Examination
• The Internal State of an LLM Knows When It's Lying
• SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models
• Language Models (Mostly) Know What They Know
• On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?
• Self-Consistency Improves Chain of Thought Reasoning in Language Models
• Survey of Hallucination in Natural Language Generation
• DialFact: A Benchmark for Fact-Checking in Dialogue
• TruthfulQA: Measuring How Models Mimic Human Falsehoods
• The Curious Case of Hallucinations in Neural Machine Translation
• Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models
• KILT: a Benchmark for Knowledge Intensive Language Tasks
• On Faithfulness and Factuality in Abstractive Summarization
• Learning the Difference that Makes a Difference with Counterfactually-Augmented Data
• FEVER: a large-scale dataset for Fact Extraction and VERification
• On Calibration of Modern Neural Networks
• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles

Cited by

• Mitigating Hallucinations in Healthcare LLMs with Granular Fact-Checking and Domain-Specific Adaptation

Related

• Theoretical Foundations and Mitigation of Hallucination in Large Language Models
• Zero-knowledge LLM hallucination detection and mitigation through fine-grained cross-model consistency
• Cost-Effective Hallucination Detection for LLMs
• The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models
• Black-Box Hallucination Detection via Consistency Under the Uncertain Expression