c769-CSDN博客

原创【文献笔记】Improving factuality in LLMs via inference-time knowledge graph construction

本文提出了一种通过推理时动态构建知识图谱来提升大语言模型(LLM)事实性的方法。该方法结合LLM内部知识与外部检索信息，分四个阶段：(1)从问题中提取初始图谱；(2)利用LLM内部知识广度优先扩展图谱；(3)通过外部检索修正和补充不完整/错误的三元组；(4)基于精炼图谱生成最终答案。实验表明，这种混合方法能有效提高事实性问答的准确性，相比单纯依赖内部知识或检索增强生成(RAG)，在三个基准数据集上均取得更好效果。该方法创新性地将结构化知识图谱与非结构化检索相结合，既保留了LLM的灵活性，又通过外部知识验证增

2025-10-09 09:56:55 806

c769的博客

原创【文献笔记】Improving factuality in LLMs via inference-time knowledge graph construction

原创【文献笔记】MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem

原创【文献笔记】The effect of ignoring routes when locating depots

原创【文献笔记】Path planning for autonomous underwater vehicles in complex environments based on PRM*

原创【文献笔记】Task allocation for multi-AUV system: A review

原创【文献笔记】Research on mult-AUVs task allocation with energy constraints in underwater search environment

原创【文献笔记】Coverage path planning for multi-AUV considering ocean currents and sonar performance

原创【文献笔记】LLM for Large-Scale Optimization Model Auto-Formulation

原创【文献笔记】Multi-objective infeasibility diagnosis for routing problems using large language models

原创【文献笔记】Maximum coverage capacitated facility location problem with range constrained drones

原创【文献笔记】ARS: Automatic Routing Solver with Large Language Models

原创【文献笔记】From words to routes: Applying large language models to vehicle routing

原创【文献笔记】Training Large Language Models to Reason in a Continuous Latent Space

原创【文献笔记】Automatic Chain of Thought Prompting in Large Language Models

原创【文献笔记】ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs

原创【文献笔记】Tree of Thoughts: Deliberate Problem Solving with Large Language Models

原创【文献笔记】Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate

原创【文献笔记】Improving factuality and reasoning in language models through multiagent debate

原创【文献笔记】LLMOPT: Learning to define and solve general optimization problems from scratch

原创【文献笔记】OR-LLM-agent:Automating modeling and solving of OR optimization problem with reasoning LLM

原创【文献笔记】DRoC: Elevating LLM for complex vehicle routing via decomposed retrieval of constraints

原创【文献笔记】LLM-based control code generation using image recognition

原创【文献笔记】SatLM: Satisfiability-Aided Language Models Using Declarative Prompting

原创【文献笔记】Knowledge Pyramid Construction for Multi-Level Retrieval-Augmented Generation

原创【文献笔记】LLM-based and retrieval-augmented control code generation

原创【文献笔记】From informal to formal: incorporating and evaluating LLM on natural language requirements

原创【文献笔记】SoS1: O1 and R1-Like Reasoning LLMs are Sum-of-Square Solvers

原创【文献笔记】Chain-of-thought reasoning without prompting

原创【文献笔记】Leveraging LLM agents for AOM for SASP problems A graph-RAG based approach

原创【文献笔记】Leveraging large language models to develop heuristics for emerging optimization problems

原创【文献笔记】OptiChat：Bridging optimization models and practitioners with large language models

原创【文献笔记】OptiMUS: Scalable optimization modeling with (MI)LP solvers and large language models

原创【文献笔记】Diagnosing Infeasible Optimization Problems Using Large Language Models

原创【文献笔记】Large Language Models as Evolutionary Optimizers

原创关于Unity Camera没有Clear Flags的解决方法

空空如也

空空如也