用智能助手增强大模型，减少幻觉，提升复杂任务推理能力
AssistRAG: Boosting the Potential of Large Language Models with an Intelligent Information Assistant
- 引入智能信息助理，通过工具调用和记忆管理辅助大模型决策
- 在多个基准上显著超越现有方法，尤其对小型模型提升明显
- 无需频繁重训，保护基础模型能力，适合资源有限的场景
大型语言模型（LLMs）虽推动了自然语言处理的发展，但常产生事实性错误，即“幻觉”。早期检索增强生成（RAG）方法如“检索-阅读”框架难以应对复杂推理任务。后续基于提示的RAG策略和监督微调（SFT）虽提升了性能，但需频繁再训练，且可能破坏基础模型能力。为此，我们提出基于助手的检索增强生成（AssistRAG），在大模型中集成智能信息助理，通过工具使用、动作执行、记忆构建和计划制定来管理知识与记忆。采用两阶段训练：课程助手学习与强化偏好优化。实验表明，AssistRAG显著优于基准方法，尤其在低阶大模型上表现更优，展现出更强的推理能力和更准确的回答。
原文摘要 · Abstract (English)
The emergence of Large Language Models (LLMs) has significantly advanced natural language processing, but these models often generate factually incorrect information, known as "hallucination". Initial retrieval-augmented generation (RAG) methods like the "Retrieve-Read" framework was inadequate for complex reasoning tasks. Subsequent prompt-based RAG strategies and Supervised Fine-Tuning (SFT) methods improved performance but required frequent retraining and risked altering foundational LLM capabilities. To cope with these challenges, we propose Assistant-based Retrieval-Augmented Generation (AssistRAG), integrating an intelligent information assistant within LLMs. This assistant manages memory and knowledge through tool usage, action execution, memory building, and plan specification. Using a two-phase training approach, Curriculum Assistant Learning and Reinforced Preference Optimization. AssistRAG enhances information retrieval and decision-making. Experiments show AssistRAG significantly outperforms benchmarks, especially benefiting less advanced LLMs, by providing superior reasoning capabilities and accurate responses.
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。