UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations
- 类型:arxiv
- 标识:2608.10835
- 链接:https://arxiv.org/abs/2608.10835
- 主分类:multimodal
- 形态:method
- 被引:0
- 被引来源:Semantic Scholar
- S2被引:0
- 影响力被引:0
- TLDR:UniProbe is introduced, a lightweight, unified, learnable detector that models a frozen LVLM's heterogeneous computational trace from a single forward pass and achieves state-of-the-art token-level and object-hallucination detection.
- 待LLM分类:否
- 标题中文:UniProbe:一种利用多结构内部表示的可学习 token 级 VLM 幻觉检测器
- TLDR中文:提出 UniProbe,一个轻量、统一、可学习的检测器,通过单次前向传播建模冻结 LVLM 的异构计算 trace,在 token 级和物体级幻觉检测上达到 SOTA。
- 来源文件:
- /inbox/tom/_candidates/2026-08-17-agent-rag-longcontext-candidates.json
- [S2 enrich]