带检索器的指令语言模型是强大的实体链接器
Instructed Language Models with Retrievers Are Powerful Entity Linkers
AI总结：
针对生成式大语言模型存在幻觉、不适用于实体链接任务的问题，提出带轻量级检索器的指令式生成实体链接器INSGENEL，在提升4倍速度的同时，平均F1值较以往生成式方案提升6.8个点，且训练数据与计算效率更高。
摘要：
由大语言模型（LLM）驱动的生成式方法已在需要复杂推理能力的任务中展现出涌现能力。但其生成本质仍导致生成内容存在幻觉问题，因此不适用于实体链接（EL）这类需要在大型知识库上进行精确实体预测的以实体为中心的任务。我们提出了指令式生成实体链接器（INSGENEL），这是首个让通用语言模型能够在知识库上执行实体链接的方法。本研究提出了多种赋予语言模型实体链接能力的方法，包括：（i）结合指令微调的序列到序列实体链接训练目标；（ii）一种基于轻量级潜在提及检索器的新型生成式实体链接框架，该框架使模型摆脱了繁重且无法并行的解码过程，实现了4倍的速度提升，且链接指标不受影响。INSGENEL的性能优于以往的生成式方案，平均F1值提升6.8个点，在训练数据效率和训练计算消耗方面也具备巨大优势。此外，我们精心设计的用于实体链接的上下文学习（ICL）框架仍显著落后于INSGENEL，再次证实实体链接任务仍是通用大语言模型的持续难题。
英文摘要：
Generative approaches powered by large language models (LLMs) have demonstrated emergent abilities in tasks that require complex reasoning abilities. Yet the generative nature still makes the generated content suffer from hallucinations, thus unsuitable for entity-centric tasks like entity linking (EL) requiring precise entity predictions over a large knowledge base. We present Instructed Generative Entity Linker (INSGENEL), the first approach that enables casual language models to perform entity linking over knowledge bases. Several methods to equip language models with EL capability were proposed in this work, including (i) a sequence-to-sequence training EL objective with instruction-tuning, (ii) a novel generative EL framework based on a light-weight potential mention retriever that frees the model from heavy and non-parallelizable decoding, achieving 4$\times$ speedup without compromise on linking metrics. INSGENEL outperforms previous generative alternatives with +6.8 F1 points gain on average, also with a huge advantage in training data efficiency and training compute consumption. In addition, our skillfully engineered in-context learning (ICL) framework for EL still lags behind INSGENEL significantly, reaffirming that the EL task remains a persistent hurdle for general LLMs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
