用少量可学习嵌入增强隐藏状态，检测大模型幻觉
Prompt Embedding Probes (PEP): Hallucination Detection in LLMs from Hidden States
- 在冻结模型基础上，用可学习提示嵌入增强探测能力
- 在TriviaQA等数据集上比传统线性探测提升检测效果
- 适合需要轻量级幻觉检测的部署场景
大型语言模型虽能生成流畅回答，但仍易产生幻觉。本文提出提示嵌入探测（Prompt Embedding Probes, PEP），一种基于冻结模型隐藏状态的白盒答案级幻觉检测方法。PEP通过在输入中加入少量可学习的提示嵌入，扩展标准线性探测。我们在TrivQA、GSM8K和MedQA数据集上使用不同规模的Qwen3模型评估了PEP。在主要分布内设置下，PEP优于标准线性探测。进一步评估显示，PEP在生成前预测和跨模型迁移中依然有效，但跨数据集泛化仍具挑战。结果表明，基于提示的适配可在保持主干冻结的同时，仅增加少量可训练参数，显著增强隐藏状态探测能力。
原文摘要 · Abstract (English)
Large language models (LLMs) can generate fluent and useful responses but remain prone to hallucinations. We introduce Prompt Embedding Probes (PEP), a white-box method for answer-level hallucination detection from the hidden states of a frozen LLM. PEP extends standard linear probes by augmenting the input with a small number of learnable prompt embeddings. We evaluate PEP on TriviaQA, GSM8K, and MedQA using Qwen3 models at multiple scales. PEP improves hidden-state-based detection over standard linear probes in the main in-distribution setting. We further evaluate PEP for pre-generation prediction, cross-model transfer, and out-of-distribution generalization. PEP remains effective in the pre-generation and cross-model settings, whereas robust cross-dataset transfer remains difficult. These results show that prompt-based adaptation can strengthen hidden-state probing while keeping the backbone frozen and adding only a small number of trainable parameters.
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。