模型输出不一致是隐患，减少冗余路径可提升可靠性。
Hallucinations Live in Variance
- 用同义改写测试模型一致性，发现输出波动源于内部路径不稳。
- 稀疏化至32%时，模型自洽率从23.8%升至55.9%。
- 适合评估智能体系统可靠性，尤其关注多步推理稳定性。
评估基准衡量模型是否正确，但不反映其是否可靠。这对单次推理影响不大，但在智能体系统中至关重要——同一问题的微小表述变化可能引发多步执行中的连锁错误。现有评估无法捕捉此类不稳定性。幻觉存在于方差中：当语义等价的提示激活不同内部路径，导致输出分歧，即为幻觉。一致但错误的输出反映偏差或知识缺失；自信的错误猜测体现校准失败。根据此定义，这两者均非幻觉。当错误由方差主导时，减少冗余路径可提升可靠性，无需增加知识。我们提出语义稳定性（SS），通过生成k个同义改写并贪婪解码，计算模式一致性（PC@k）进行测量。SS是诊断方差驱动不可靠性的工具，而非提升准确性的方法。实验显示，密集Qwen3-0.6B仅23.8%时间与自身一致；在32%稀疏度下，一致率跃升至55.9%。相图揭示了方差降低超过偏差积累的最优区间，以及稳定性崩溃于错误答案的临界区域。
原文摘要 · Abstract (English)
Benchmarks measure whether a model is correct. They do not measure whether a model is reliable. This distinction is largely academic for single-shot inference, but becomes critical for agentic AI systems, where a single rephrased prompt can trigger cascading failures in multi-step execution. Yet this form of instability is not captured by existing evaluations. Hallucinations live in variance: they arise when semantically equivalent prompts activate inconsistent internal pathways, producing divergent outputs. Consistent but incorrect outputs reflect bias or missing knowledge; confident guessing reflects calibration failure. Neither constitutes hallucination under this definition. When error is variance-dominated, reducing redundant pathways improves reliability without adding knowledge. We formalize this through Semantic Stability (SS), measured via Paraphrase Consistency (PC@k): generate k paraphrases, greedy decode each, compute mode agreement. SS is a diagnostic for variance-driven unreliability, not a method for improving correctness. We show that a dense Qwen3-0.6B agrees with itself only 23.8% of the time; at 32% sparsity, agreement jumps to 55.9%. A phase diagram reveals the sweet spot where variance reduction outpaces bias accumulation, and regimes where stability collapses onto wrong answers.
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。