研究大模型回答的不确定性，发现熵值可判断知识类问题难易度。
When an LLM is apprehensive about its answers -- and when its uncertainty is justified
- 用词元熵和模型自评评估不同题型的不确定性
- 生物类问题熵值预测错误率AUC达0.73，数学类仅为0.55
- 现有数据集需平衡推理量，避免评估偏差
不确定性估计对评估大语言模型至关重要，尤其在高风险场景中。本文研究了在14个不同主题的多选题任务中，词元熵与模型作为裁判（MASJ）两种方法的表现。实验涵盖三个不同规模的模型（Phi-4、Mistral、Qwen，1.5B至72B）。结果表明，MASJ表现接近随机猜测；而响应熵在知识依赖型领域（如生物）能有效预测错误，其ROC AUC为0.73；但在推理依赖型领域（如数学），相关性消失（数学类ROC-AUC为0.55）。进一步发现，熵值估计需依赖模型推理量，因此应在不确定性框架中整合数据不确定性；同时，现有MMLU-Pro数据集存在推理量偏差，需平衡各子领域的推理需求以实现公平评估。
原文摘要 · Abstract (English)
Uncertainty estimation is crucial for evaluating Large Language Models (LLMs), particularly in high-stakes domains where incorrect answers result in significant consequences. Numerous approaches consider this problem, while focusing on a specific type of uncertainty, ignoring others. We investigate what estimates, specifically token-wise entropy and model-as-judge (MASJ), would work for multiple-choice question-answering tasks for different question topics. Our experiments consider three LLMs: Phi-4, Mistral, and Qwen of different sizes from 1.5B to 72B and $14$ topics. While MASJ performs similarly to a random error predictor, the response entropy predicts model error in knowledge-dependent domains and serves as an effective indicator of question difficulty: for biology ROC AUC is $0.73$. This correlation vanishes for the reasoning-dependent domain: for math questions ROC-AUC is $0.55$. More principally, we found out that the entropy measure required a reasoning amount. Thus, data-uncertainty related entropy should be integrated within uncertainty estimates frameworks, while MASJ requires refinement. Moreover, existing MMLU-Pro samples are biased, and should balance required amount of reasoning for different subdomains to provide a more fair assessment of LLMs performance.
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。