Large Language Models, Knowledge Graphs and Search Engines: A Crossroads for Answering Users' Questions

2025-01-12

AI Summary

Current large language models (LLMs), knowledge graphs (KGs), and search engines suffer from insufficient coordination in addressing users’ diverse, multi-level information needs. Method: We propose the first user-centered, fine-grained information need taxonomy, systematically characterizing the applicability boundaries of LLMs, KGs, and search engines along four dimensions—factual accuracy, explanatory depth, temporal freshness, and query complexity. We further design a dynamic collaborative question-answering framework that integrates LLM-based reasoning, KG-structured querying, and real-time web search, with demand-aware adaptive method selection and orchestration. Contribution/Results: This work bridges a critical gap in user-centric collaborative QA research; delivers a practical, implementation-ready roadmap for cross-technology integration; and establishes both a theoretical framework and empirical validation for adaptive QA systems.

Technology Category

• Natural Language Processing: Question Answering
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Much has been discussed about how Large Language Models, Knowledge Graphs and Search Engines can be combined in a synergistic manner. A dimension largely absent from current academic discourse is the user perspective. In particular, there remain many open questions regarding how best to address the diverse information needs of users, incorporating varying facets and levels of difficulty. This paper introduces a taxonomy of user information needs, which guides us to study the pros, cons and possible synergies of Large Language Models, Knowledge Graphs and Search Engines. From this study, we derive a roadmap for future research.

Problem

• Large Language Models
• Knowledge Graphs
• Search Engines Integration

Innovation

• taxonomy
• integrated tools
• user information needs