The paper introduces a multi‑signal pipeline for detecting hallucinations in large language model outputs, combining fine‑tuned DeBERTa‑v3 classification, Monte Carlo Dropout uncertainty, and temperature‑scaled calibration. On the HaluEval benchmark it achieves strong performance (F1 = 0.915, AUROC = 0.977) and further improves accuracy to 93.2% with MC Dropout. The authors also demonstrate that applying Direct Preference Optimization to a Qwen2.5‑0.5B generator reduces hallucination rates from 85.5% to 37.7%, and show that domain‑specific fine‑tuning (PubMedBERT on SciFact) yields better results than general‑domain training.
arXiv:2602.11166v2 Announce Type: replace-cross
Abstract: Parameter-efficient fine-tuning (PEFT) methods are widely used to adapt large language models (LLMs) to downstream tasks and are often assume...
By Xu Hu, Yifan Zhang, Songtao Wei, Chen Zhao, Qiannan Li, Bingzhe Li, Feng Chen
arXiv:2607. 04223v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) reduces but does not eliminate hallucination, and existing detectors return a single answer-level score that does not indicate which sentence is unsupported, or why.
By Mohamed Aly Bouke
arXiv:2605. 26366v3 Announce Type: replace Abstract: Recent studies on hallucination detection have shown that hallucination-related signals are more strongly encoded in intermediate layers than in the final layer of large language models (LLMs).
By Xinpeng Wang, William X. Cao, Andrew Gordon Wilson, Zhe Zeng
arXiv:2606. 29809v1 Announce Type: cross Abstract: Hallucination detection has become a pressing requirement for trustworthy AI deployment at scale.
By Kriti Faujdar, Smit Kadvani
arXiv:2606. 07528v1 Announce Type: cross Abstract: Hallucination in large language models (LLMs), defined as the generation of factually incorrect or unsupported content, remains a critical barrier to reliable deployment.
By Naveen Bera, Pulijala Sai Nikhila, Kondaguduru Abhiram, Shaik Gayaz Ali, Shoaib Sadiq Salehmohamed, Shaik Mohammed Omar, Jinal Prashant Thakkar, Hansika Aredla, Shalmali Ayachit
arXiv:2608.24492v1 Announce Type: cross
Abstract: Uncertainty quantification (UQ) methods are widely used for hallucination detection in large language models (LLMs) in closed-book settings where gro...
By Mohit Singh Chauhan, Vipin Gyanchandani, Dylan Bouchard
Uncertainty quantification (UQ) methods are widely used for hallucination detection in large language models (LLMs) in closed-book settings where ground-truth evidence is unavailable at inference time...
arXiv:2507. 18043v2 Announce Type: replace-cross Abstract: Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at test time without updating model weights.
By Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal
OmniHallu is a unified framework for detecting hallucinations in multimodal large language models across both comprehension and generation tasks involving image, video, and audio modalities. It introduces OmniHallu-Bench, a 10,000-sample benchmark with claim-level human annotations for six cross-modal tasks (I2T, V2T, A2T, T2I, T2V, T2A). The system uses a multi‑agent architecture that decomposes outputs into atomic claims, verifies them with modality‑specific experts, and aggregates evidence through structured reasoning, while a preference‑optimized verifier reduces expert calls by 66% with minimal performance loss.
By Jianjiang Yang, Peihang Li, Shanqing Xu, Mengchen Qian, Lu Zhang, Meng Luo
The paper introduces a token‑level hallucination detector that treats hallucinations as temporally extended spans and uses sequence labeling. It fuses 33‑dimensional features from text statistics, NLI entailment, and language‑model surprisal, and applies a BiGRU to achieve an AUC of 0.840 on RAGTruth, outperforming a logistic‑regression baseline by 11 points. The study shows that temporal ordering of features, rather than model capacity, drives most of the performance gain, and the detector remains effective on unseen language models with less than 4% AUC loss.
By Igor Itkin
The paper introduces Variance‑Calibrated Modulation (VCM), a training‑free pre‑decoding technique that reshapes language model probability distributions before truncation. VCM uses two dynamic mechanisms: a Contextual Searchlight via PMI to suppress stopwords and highlight context‑relevant tokens, and an Adaptive Self‑Debiasing that applies scale‑invariant penalization based on real‑time logit standard deviation. Experiments on open‑ended generation, factual QA, and mathematical reasoning show that VCM consistently reduces the likelihood trap, improving diversity, coherence, and reasoning accuracy with minimal computational cost.
By Yuanhao Ding, Meimingwei Li, Esteban Garces Arias, Matthias A{\ss}enmacher, Christian Heumann, Chongsheng Zhang