Domain-Specific Hallucination Detection in Large Language Models
A multi-signal pipeline detects LLM hallucinations, reaching F1 0.915 on HaluEval and cutting Qwen2.5-0.5B hallucination rates from 85.5% to 37.7% via DPO.
The paper presents a hallucination detection pipeline combining fine-tuned DeBERTa-v3 classification, Monte Carlo Dropout uncertainty, and temperature-scaled calibration. It achieves F1 0.915 and AUROC 0.977 on general-domain HaluEval tasks, with MC Dropout inference raising accuracy to 93.2%. Applying DPO to a Qwen2.5-0.5B generator reduces its hallucination rate from 85.5% to 37.7%, while cross-domain evaluation shows poor general-domain transfer to SciFact (F1 0.52) and PubMedBERT fine-tuning as the strongest adaptation (F1 0.63).
- F1 0.915 and AUROC 0.977 on general-domain HaluEval tasks
- DPO reduces Qwen2.5-0.5B hallucination rate from 85.5% to 37.7%
- General-domain detectors transfer poorly to biomedical text (SciFact F1 0.52)
- PubMedBERT fine-tuning is the strongest domain adaptation (F1 0.63)
- Context ablation confirms genuine entailment rather than surface patterns
- Tags
- calibrationdeberta-v3dpohallucination-detectionhaluevalmonte-carlo-dropoutpubmedbertqwen2.5-0.5b
- Organizations
- arXiv
- AI models
- DeBERTa-v3Qwen2.5-0.5BPubMedBERT
From the original article
1 min read at arxiv.orgLarge language models generate fluent text that can contain unfaithful claims -- a phenomenon known as hallucination. We present a multi-signal detection pipeline combining fine-tuned DeBERTa-v3 classification, Monte Carlo (MC) Dropout uncertainty quantification, and temperature-scaled calibration for response-level hallucination detection. Evaluated on the HaluEval benchmark, our pipeline achieves F1=0.
By Varun Teja Chundru · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.