用智能路由让大模型只在关键处推理，提升实体链接效率与精度。
Leveraging the Power of Large Language Models in Entity Linking via Adaptive Routing and Targeted Reasoning
- 分两步处理：简单案例用轻量模型，复杂案例才调用大模型推理。
- 在6个数据集上平均提升2.53%，最高达4.47%性能增益。
- 相比全量使用大模型，节省一半以上推理tokens，适合部署场景。
实体链接（EL）传统依赖大规模标注数据和深度微调。近期少样本方法通过提示词利用大语言模型（LLM）减少训练需求，但常因昂贵的LLM推理导致效率低下。ARTER（自适应路由与目标实体推理）提出一种结构化流程，在无需深度微调的情况下实现高精度：通过候选生成、基于上下文的评分、自适应路由和选择性推理，对检索出的候选实体计算少量互补信号（嵌入与LLM-based），将上下文提及分类为易例与难例。易例由低计算量实体链接器（如ReFinED）处理，难例则交由更耗资源的针对性LLM推理。在标准基准测试中，ARTER相较ReFinED最高提升4.47%，5/6数据集平均提升2.53%，性能媲美全量使用LLM推理的方案，同时在LLM token消耗上减少约50%。
原文摘要 · Abstract (English)
Entity Linking (EL) has traditionally relied on large annotated datasets and extensive model fine-tuning. While recent few-shot methods leverage large language models (LLMs) through prompting to reduce training requirements, they often suffer from inefficiencies due to expensive LLM-based reasoning. ARTER (Adaptive Routing and Targeted Entity Reasoning) presents a structured pipeline that achieves high performance without deep fine-tuning by strategically combining candidate generation, context-based scoring, adaptive routing, and selective reasoning. ARTER computes a small set of complementary signals(both embedding and LLM-based) over the retrieved candidates to categorize contextual mentions into easy and hard cases. The cases are then handled by a low-computational entity linker (e.g. ReFinED) and more expensive targeted LLM-based reasoning respectively. On standard benchmarks, ARTER outperforms ReFinED by up to +4.47%, with an average gain of +2.53% on 5 out of 6 datasets, and performs comparably to pipelines using LLM-based reasoning for all mentions, while being as twice as efficient in terms of the number of LLM tokens.
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。