用邻居一致性检测大模型回答是否经得起轻微干扰，更真实可靠。
Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency
- 通过测试同一概念邻域内回答的一致性，评估模型信念鲁棒性。
- 高邻居一致性数据在上下文扰动下表现更稳定，错误率低30%。
- 适合关注模型可信度、部署安全性的研究者和开发者。
随着大语言模型（LLMs）在现实场景中广泛应用，仅保证答案正确已不够。可靠部署需确保模型在上下文扰动下仍保持真实信念。现有评估多依赖自一致性等点级置信度，可能掩盖模型信念的脆弱性。我们发现，即使某些事实回答的自一致性达到完美，也可能在轻微上下文干扰下迅速崩溃。为此，我们提出邻居一致性信念（NCB），一种衡量信念结构鲁棒性的指标，评估模型在概念邻域内的回答一致性。为验证其有效性，引入新型认知压力测试协议，探测输出在上下文干扰下的稳定性。跨多个LLM的实验表明，高NCB数据对干扰更具抵抗力。最后，提出结构感知训练（SAT），优化不变信念结构，使长尾知识脆弱性降低约30%。代码已开源：https://github.com/zjunlp/belief。
原文摘要 · Abstract (English)
As Large Language Models (LLMs) are increasingly deployed in real-world settings, correctness alone is insufficient. Reliable deployment requires maintaining truthful beliefs under contextual perturbations. Existing evaluations largely rely on point-wise confidence like Self-Consistency, which can mask brittle belief. We show that even facts answered with perfect self-consistency can rapidly collapse under mild contextual interference. To address this gap, we propose Neighbor-Consistency Belief (NCB), a structural measure of belief robustness that evaluates response coherence across a conceptual neighborhood. To validate the efficiency of NCB, we introduce a new cognitive stress-testing protocol that probes outputs stability under contextual interference. Experiments across multiple LLMs show that the performance of high-NCB data is relatively more resistant to interference. Finally, we present Structure-Aware Training (SAT), which optimizes context-invariant belief structure and reduces long-tail knowledge brittleness by approximately 30%. Code is available at https://github.com/zjunlp/belief.
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。