Structure the unstructured // LLMs, reasoning and structured info
The ability of LLMs to generate and analyze valid structured information unlocks new, useful applications
Reasoning is required abilities to process structured and unstructured information and mix it up.
Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) in many knowledge-based tasks. However, existing RAG methods struggle with knowledge-intensive reasoning tasks, because useful information required to these tasks are badly scattered. This characteristic makes it difficult for existing RAG methods to accurately identify key information and perform global reasoning with such noisy augmentation. In this paper, motivated by the cognitive theories that humans convert raw information into various structured knowledge when tackling knowledge-intensive reasoning, we proposes a new framework, StructRAG, which can identify the optimal structure type for the task at hand, reconstruct original documents into this structured format, and infer answers based on the resulting structure. Extensive experiments across various knowledge-intensive tasks show that StructRAG achieves state-of-the-art performance, particularly excelling in challenging scenarios, demonstrating its potential as an effective solution for enhancing LLMs in complex real-world applications.
Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant responses tailored to user needs. However, existing RAG systems have significant limitations, including reliance on flat data representations and inadequate contextual awareness, which can lead to fragmented answers that fail to capture complex inter-dependencies. To address these challenges, we propose LightRAG, which incorporates graph structures into text indexing and retrieval processes. This innovative framework employs a dual-level retrieval system that enhances comprehensive information retrieval from both low-level and high-level knowledge discovery. Additionally, the integration of graph structures with vector representations facilitates efficient retrieval of related entities and their relationships, significantly improving response times while maintaining contextual relevance. This capability is further enhanced by an incremental update algorithm that ensures the timely integration of new data, allowing the system to remain effective and responsive in rapidly changing data environments. Extensive experimental validation demonstrates considerable improvements in retrieval accuracy and efficiency compared to existing approaches. We have made our LightRAG open-source and available at the link: https://github.com/HKUDS/LightRAG.
Existing retrieval-based reasoning approaches for large language models (LLMs) heavily rely on the density and quality of the non-parametric knowledge source to provide domain knowledge and explicit reasoning chain. However, inclusive knowledge sources are expensive and sometimes infeasible to build for scientific or corner domains. To tackle the challenges, we introduce Graph Inspired Veracity Extrapolation (GIVE), a novel reasoning framework that integrates the parametric and non-parametric memories to enhance both knowledge retrieval and faithful reasoning processes on very sparse knowledge graphs. By leveraging the external structured knowledge to inspire LLM to model the interconnections among relevant concepts, our method facilitates a more logical and step-wise reasoning approach akin to experts’ problem-solving, rather than gold answer retrieval. Specifically, the framework prompts LLMs to decompose the query into crucial concepts and attributes, construct entity groups with relevant entities, and build an augmented reasoning chain by probing potential relationships among node pairs across these entity groups. Our method incorporates both factual and extrapolated linkages to enable comprehensive understanding and response generation. Extensive experiments on reasoning-intense benchmarks on biomedical and commonsense QA demonstrate the effectiveness of our proposed method. Specifically, GIVE enables GPT3.5-turbo to outperform advanced models like GPT4 without any additional training cost, thereby underscoring the efficacy of integrating structured information and internal reasoning ability of LLMs for tackling specialized tasks with limited external resources.
— -
We propose Graph Inspired Veracity Extrapolation (GIVE), a knowledge extrapolation framework for structured reasoning of LLM on sparse knowledge graphs. GIVE neither focuses on explicit 10 information retrieval, nor relies on improving the internal reasoning ability of LLMs by appending triggering statements to the query. It utilizes the high-level thinking processes mined in sparse knowledge graphs to combine both approaches. It retrieves the most relevant information in the knowledge base and, at the same time, inspires LLM to exploit its internal knowledge by conducting structured reasoning and knowledge extrapolation. GIVE enables GPT3.5-turbo to achieve better performance than GPT4 on biomedical QA benchmarks with a very sparse knowledge graph and mitigates the hallucination issue of retrieval-based methods on sparse KG. It sheds light on the potential of LLM to conduct divergent thinking using very limited external clues.
Recently, Knowledge Graphs (KGs) have been successfully coupled with Large Language Models (LLMs) to mitigate their hallucinations and enhance their reasoning capability, e.g., KG-based retrieval-augmented framework. However, current KG-LLM frameworks lack rigorous uncertainty estimation, limiting their reliable deployment in high-stakes applications Directly incorporating uncertainty quantification into KG-LLM frameworks presents challenges due to their complex architectures and the intricate interactions between the knowledge graph and language model components. To address this crucial gap, we propose a new trustworthy KG-LLM framework, UAG (Uncertainty Aware Knowledge-Graph Reasoning), which incorporates uncertainty quantification into the KG-LLM framework. We design an uncertainty-aware multi-step reasoning framework that leverages conformal prediction to provide a theoretical guarantee on the prediction set. To manage the error rate of the multi-step process, we additionally introduce an error rate control module to adjust the error rate within the individual components. Extensive experiments show that UAG can achieve any pre-defined coverage rate while reducing the prediction set/interval size by 40% on average over the baselines.
In this paper, we tackle the challenge of uncertainty quantification in knowledge graph question answering by integrating conformal prediction with KG-LLM models. Our architecture leverages the Learn Then Test (LTT) framework for multi-step calibration, delivering reliable results that meet pre-defined error rates while maintaining practical prediction set sizes. Extensive experiments show our method’s effectiveness in balancing accuracy and uncertainty, making it suitable for real-world applications. While our focus is on knowledge graphs, this approach can be extend to open-domain QA, although challenges remain due to the lack of structured graph properties in such settings. Future work can explore these adaptations and ensure robust uncertainty quantification across various tasks.
Although large language models (LLMs) have achieved significant success in various tasks, they often struggle with hallucination problems, especially in scenarios requiring deep and responsible reasoning. These issues could be partially addressed by introducing external knowledge graphs (KG) in LLM reasoning. In this paper, we propose a new LLM-KG integrating paradigm “LLM ⊗ KG” which treats the LLM as an agent to interactively explore related entities and relations on KGs and perform reasoning based on the retrieved knowledge. We further implement this paradigm by introducing a new approach called Think-on-Graph (ToG), in which the LLM agent iteratively executes beam search on KG, discovers the most promising reasoning paths, and returns the most likely reasoning results. We use a number of well-designed experiments to examine and illustrate the following advantages of ToG: 1) compared with LLMs, ToG has better deep reasoning power; 2) ToG has the ability of knowledge traceability and knowledge correctability by leveraging LLMs reasoning and expert feedback; 3) ToG provides a flexible plugand-play framework for different LLMs, KGs and prompting strategies without any additional training cost; 4) the performance of ToG with small LLM models could exceed large LLM such as GPT-4 in certain scenarios and this reduces the cost of LLM deployment and application. As a training-free method with lower computational cost and better generality, ToG achieves overall SOTA in 6 out of 9 datasets where most previous SOTAs rely on additional training. Our code is publicly available at https://github.com/IDEA-FinAI/ToG.
