The paper proposes a hidden‑state probing method for detecting hallucinations at the span level in large language model outputs, moving beyond token‑wise binary classification. By examining layer‑wise activation patterns, the approach identifies the exact onset and continuation tokens of hallucinations, achieving higher precision‑recall AUC than random baselines despite class imbalance. Additionally, the authors introduce a cross‑model detection framework where one model observes another’s internal representations, showing that an external observer can match or surpass the generator’s own self‑detection of hallucination onsets, even when the observer is smaller.
By Kingshuk Gupta, Davide Buscaldi
arXiv:2608. 16353v1 Announce Type: cross Abstract: Even well-aligned large language models confidently generate factually incorrect text, making hallucination a persistent reliability risk in high-stakes deployments.
By Zhihao Guo, Zonghan Wu, Huan Huo, DaYong Ye, Junwei Zhang, Weiran Yao, Zhiwei Liu, Qingsong Wen, Yilei Shao
Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks, yet they remain prone to generating hallucinations. Detecting these hallucinations is critical for deploying LLMs reliably in high-stakes applications.
The paper introduces a multi‑signal pipeline for detecting hallucinations in large language models, combining fine‑tuned DeBERTa‑v3 classification, Monte Carlo Dropout uncertainty, and temperature‑scaled calibration. On the HaluEval benchmark it achieves high performance (F1 = 0.915, AUROC = 0.977) across QA, summarization, and dialogue, and shows that 25 % of training data yields 77 % of full‑data performance. The authors also demonstrate that applying Direct Preference Optimization to a Qwen2.5‑0.5B generator cuts hallucination rates from 85.5 % to 37.7 %, and that domain‑specific fine‑tuning (PubMedBERT on SciFact) outperforms general‑domain models for biomedical text.
By Varun Teja Chundru, Debasmita Biswas
arXiv:2608. 08024v1 Announce Type: cross Abstract: Large language models (LLMs) can generate fluent and useful responses but remain prone to hallucinations.
By Zakhar Mrykhin, Valentin Malykh
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
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:2601. 06196v3 Announce Type: replace-cross Abstract: Large language models (LLMs) frequently generate factually incorrect or unsupported content, commonly referred to as hallucinations.
By Bodla Krishna Vamshi, Rohan Bhatnagar, Haizhao Yang
The paper introduces InnerExpert, a method that uses Mixture-of-Experts (MoE) internal signals—such as router entropy, expert disagreement, and usage patterns—to detect hallucinations at the token level in large language models. By combining these MoE-specific signals with standard transformer features into compact per-token vectors, InnerExpert trains a lightweight detector using an LLM-as-a-judge pipeline, enabling continuous updates without manual labeling. Experiments across five datasets and two MoE architectures show that InnerExpert outperforms existing methods, achieving up to 0.91 answer-level and 0.76 token-level AUROC with only a single forward pass.
arXiv:2602. 02888v2 Announce Type: replace-cross Abstract: Hallucinations remain a major obstacle for large language models (LLMs), especially in safety-critical domains.
By Ahmad Shapiro, Karan Taneja, Ashok Goel
arXiv:2602. 07253v3 Announce Type: replace Abstract: Detecting hallucinations in large language models is a critical open problem with significant implications for safety and reliability.
By Litian Liu, Reza Pourreza, Yubing Jian, Yao Qin, Roland Memisevic
The paper introduces InnerExpert, a method that uses Mixture-of-Experts (MoE) architecture signals—such as router entropy, expert disagreement, and usage patterns—to detect hallucinations at the token level in Large Language Models. By combining these MoE-specific signals with standard transformer features into compact per-token vectors, InnerExpert trains a lightweight detector using an LLM-as-a-judge pipeline, enabling continuous updates without manual labeling. Experiments across five datasets and two MoE architectures show that InnerExpert outperforms existing methods, achieving up to 0.91 answer-level and 0.76 token-level AUROC with only a single forward pass.
By Joao Fonseca, Rodrigo Rodrigues, Paolo Romano