用几何密度脊线检测大模型幻觉，少标签下仍稳定有效
Density Ridge Selective Prediction for LLM and VLM Hallucination Detection under Calibration Label Scarcity
- 基于隐藏状态轨迹的六维特征，构建输出分布的几何骨架
- 在6个基准上比现有方法高5-20点AUROC，标签稀缺时更稳健
- 适合低资源场景下的幻觉检测，尤其适合无标注或少标注任务
大语言模型和视觉语言模型的幻觉检测正转向选择性预测：检测器给出置信度，低置信时放弃判断。无监督采样方法（语义熵）无需标签但性能受限；有监督探针虽在分布内表现好，但在校准标签稀缺时性能急剧下降。本文将大模型的响应流形重构为基于六维运动学特征图的核密度估计的密度脊线，通过测试生成点到最近脊线顶点的负欧氏距离进行评分，获得低维几何骨架以表征随机输出分布。在六个问答基准（HaluEval-QA、TriviaQA、GSM8K、POPE、ScienceQA、A-OKVQA）上，使用八种文本与视觉大模型，在刻意稀疏标签设置（$n_{\text{cal}}{=}200$ 查询，$N{=}5$ 生成）下评估。基于脊线的评分在AUROC上提升5-20点，且在标签稀缺时表现出更温和的退化。
原文摘要 · Abstract (English)
Hallucination detection in large language and vision-language models is increasingly framed as selective prediction, where a detector assigns a confidence score and abstains when confidence is low. Unsupervised sampling detectors (Semantic Entropy) avoid labels but plateau in quality, while supervised probes attain stronger in-distribution scores yet degrade sharply when calibration labels are scarce. We recover the response manifold of an LLM as the density ridge of a kernel density estimate built on a six-dimensional kinematic feature map of hidden state generation trajectories. A test generation is scored by the negated Euclidean distance from its projected feature point to the nearest ridge vertex, yielding a low-dimensional geometric skeleton of the stochastic output distribution. We evaluate against Semantic Entropy, topological methods, and log-probability on six QA benchmarks (HaluEval-QA, TriviaQA, GSM8K, POPE, ScienceQA, A-OKVQA) using eight text and vision LLMs in a deliberately label-scarce protocol ($n_{\text{cal}}{=}200$ queries, $N{=}5$ generations). Our ridge-based score beats on AUROC with 5-20 points gain, while demonstrating tempered degradation under calibration-label scarcity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。