用贝叶斯方法让问答模型学会说‘不知道’，提升可靠性与伦理安全性。
Toward Ethical AI Through Bayesian Uncertainty in Neural Question Answering
- 通过贝叶斯推断量化模型预测不确定性，实现置信度评估。
- 在CommonsenseQA上验证，低置信度时选择拒答可提升整体可靠性。
- 适合关注AI伦理、可信决策和鲁棒性系统的研究人员参考。
本文探索贝叶斯推理在神经网络问答系统中量化不确定性的能力。从鸢尾花数据集上的多层感知机出发，展示后验推断如何反映预测置信度；进而扩展至语言模型，先对冻结的头部应用贝叶斯推断，最终应用于LoRA微调的Transformer模型，在CommonsenseQA基准上进行评估。研究不追求最高准确率，而是对比拉普拉斯近似与最大后验（MAP）估计，突出不确定性校准与选择性预测能力。当置信度低时，模型可主动选择不回答，这种“我不知道”的响应不仅增强可解释性，也展示了贝叶斯方法在推动更负责任、更伦理的神经问答系统部署中的潜力。
原文摘要 · Abstract (English)
We explore Bayesian reasoning as a means to quantify uncertainty in neural networks for question answering. Starting with a multilayer perceptron on the Iris dataset, we show how posterior inference conveys confidence in predictions. We then extend this to language models, applying Bayesian inference first to a frozen head and finally to LoRA-adapted transformers, evaluated on the CommonsenseQA benchmark. Rather than aiming for state-of-the-art accuracy, we compare Laplace approximations against maximum a posteriori (MAP) estimates to highlight uncertainty calibration and selective prediction. This allows models to abstain when confidence is low. An ``I don't know'' response not only improves interpretability but also illustrates how Bayesian methods can contribute to more responsible and ethical deployment of neural question-answering systems.
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。