用多重信号提前判断模型可信度，减少幻觉并节省算力。
Confidence-Aware Routing for Large Language Model Reliability Enhancement: A Multi-Signal Approach to Pre-Generation Hallucination Mitigation
- 通过语义对齐、层间收敛和学习得分三信号评估生成前的不确定性。
- 幻觉检测准确率0.74，计算成本比事后修正低40%，F1达0.82。
- 适合追求高可靠性且资源受限的LLM应用，如医疗、法律问答。
大语言模型常产生看似合理但事实错误的内容（幻觉）。现有方法多在生成后修正，成本高且无法预防。本文提出一种置信度感知路由系统，在生成前主动评估模型不确定性，并根据可靠性将请求导向不同路径：高置信度时本地生成，中置信度时检索增强生成，低置信度时调用更大模型，极低置信度则交由人工审核。该方法融合三种互补信号：内部表征与参考嵌入的语义对齐、模型各层间的内部收敛分析、以及学习得到的置信度估计。统一置信度分数决定路由策略。在知识密集型问答基准上测试显示，幻觉检测准确率从0.42提升至0.74，计算成本降低40%，F1得分由0.61增至0.82，误报率仅0.09。该范式从被动纠错转向主动评估，显著提升大模型可靠性与效率。
原文摘要 · Abstract (English)
Large Language Models suffer from hallucination, generating plausible yet factually incorrect content. Current mitigation strategies focus on post-generation correction, which is computationally expensive and fails to prevent unreliable content generation. We propose a confidence-aware routing system that proactively assesses model uncertainty before generation and redirects queries based on estimated reliability. Our approach combines three complementary signals: semantic alignment between internal representations and reference embeddings, internal convergence analysis across model layers, and learned confidence estimation. The unified confidence score determines routing to four pathways: local generation for high confidence, retrieval-augmented generation for medium confidence, larger models for low confidence, and human review for very low confidence. Evaluation on knowledge-intensive QA benchmarks demonstrates significant improvements in hallucination detection (0.74 vs. 0.42 baseline) while reducing computational costs by 40% compared to post-hoc methods. The F1 score improves from 0.61 to 0.82 with low false positive rates (0.09). This paradigm shift from reactive correction to proactive assessment offers a computationally efficient approach to LLM reliability enhancement.
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。