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 proposes using the temporal volatility of internal attention mechanisms—measured by an unsupervised attention dispersion metric—as a diagnostic signal for hallucinations in large language models. It demonstrates that spikes in attention entropy within intermediate layers correlate with reasoning breakdowns, and shows statistically significant AUC improvements of up to +0.076 over output-based baselines on GSM8K and MATH-500 benchmarks using the Qwen2.5 model family.
By Shardul P. More, Tanuja S. Pawar
DynHD is a method for detecting hallucinations in diffusion large language models (D‑LLMs) by focusing on token‑level uncertainty and its evolution during the denoising process. It introduces a semantic‑aware evidence construction module that filters out non‑informative structural tokens and highlights uncertainty in informative tokens, and a reference evidence generator that models the expected trajectory of uncertainty, enabling a deviation‑based detector to identify hallucinations. Experiments show DynHD outperforms existing baselines while being more efficient across various benchmarks and backbone models.
By Yanyu Qian, Yue Tan, Yixin Liu, Wang Yu, Shirui Pan
The paper introduces Label-Confidence-Aware Uncertainty Quantification (LCA-UQ), a method that uses Pointwise Kullback-Leibler divergence to align global entropy from multiple stochastic samples with the local confidence of a candidate answer. By bridging this gap, LCA-UQ improves the reliability and stability of uncertainty assessments in natural language generation. Experiments on popular LLMs and NLP datasets show that label sources significantly influence classification and that LCA-UQ outperforms existing uncertainty estimation approaches.
By Qinhong Lin, Yinglun Feng, Yuhao Zhang, Zhongliang Yang, Linna Zhou
arXiv:2606. 01033v1 Announce Type: new Abstract: When a language model hallucinates, the final answer is wrong, but the mistake is not necessarily invisible inside the model.
By Bohan Yang, Yijun Gong, Zhi Zhang, Ge Zhang, Wenpeng Xing, Meng Han
arXiv:2607. 16643v1 Announce Type: new Abstract: Existing hallucination detection methods are typically conducted at the inference stage, without making any modifications to the model itself.
By Qiuyuan Li, Hongliang Dai, Piji Li