GraphNews

Reduce LLM hallucinations with RAG over textual as well as structured knowledge bases. Today we are releasing WSTaRK h, a large-scale LLM retrieval benchmark… | 22 comments on LinkedIn

How can we further increase the accuracy of LLM-powered question answering systems? Ontologies to the rescue! That is the conclusion of the latest research… | 16 comments on LinkedIn

An open-source library for building knowledge graphs from text corpus using open-source LLMs like Llama 3 and Mixtral.

Language models have achieved impressive performances on dialogue generation tasks. However, when generating responses for a conversation that requires factual knowledge, they are far from perfect, due to an absence of mechanisms to retrieve, encode, and reflect the knowledge in the generated responses. Some knowledge-grounded dialogue generation methods tackle this problem by leveraging facts from Knowledge Graphs (KGs); however, they do not guarantee that the model utilizes a relevant piece of knowledge from the KG. To overcome this limitation, we propose SUbgraph Retrieval-augmented GEneration (SURGE), a framework for generating context-relevant and knowledge-grounded dialogues with the KG. Specifically, our SURGE framework first retrieves the relevant subgraph from the KG, and then enforces consistency across facts by perturbing their word embeddings conditioned by the retrieved subgraph. Then, we utilize contrastive learning to ensure that the generated texts have high similarity to the retrieved subgraphs. We validate our SURGE framework on OpendialKG and KOMODIS datasets, showing that it generates high-quality dialogues that faithfully reflect the knowledge from KG.

Recent work demonstrated great promise in the idea of orchestrating collaborations between LLMs, human input, and various tools to address the inherent limitations of LLMs. We propose a novel perspective called semantic decoding, which frames these collaborative processes as optimization procedures in semantic space. Specifically, we conceptualize LLMs as semantic processors that manipulate meaningful pieces of information that we call semantic tokens (known thoughts). LLMs are among a large pool of other semantic processors, including humans and tools, such as search engines or code executors. Collectively, semantic processors engage in dynamic exchanges of semantic tokens to progressively construct high-utility outputs. We refer to these orchestrated interactions among semantic processors, optimizing and searching in semantic space, as semantic decoding algorithms. This concept draws a direct parallel to the well-studied problem of syntactic decoding, which involves crafting algorithms to best exploit auto-regressive language models for extracting high-utility sequences of syntactic tokens. By focusing on the semantic level and disregarding syntactic details, we gain a fresh perspective on the engineering of AI systems, enabling us to imagine systems with much greater complexity and capabilities. In this position paper, we formalize the transition from syntactic to semantic tokens as well as the analogy between syntactic and semantic decoding. Subsequently, we explore the possibilities of optimizing within the space of semantic tokens via semantic decoding algorithms. We conclude with a list of research opportunities and questions arising from this fresh perspective. The semantic decoding perspective offers a powerful abstraction for search and optimization directly in the space of meaningful concepts, with semantic tokens as the fundamental units of a new type of computation.

Neurosymbolic AI is an increasingly active area of research that combines symbolic reasoning methods with deep learning to leverage their complementary benefits. As knowledge graphs are becoming a popular way to represent heterogeneous and multi-relational data, methods for reasoning on graph structures have attempted to follow this neurosymbolic paradigm. Traditionally, such approaches have utilized either rule-based inference or generated representative numerical embeddings from which patterns could be extracted. However, several recent studies have attempted to bridge this dichotomy to generate models that facilitate interpretability, maintain competitive performance, and integrate expert knowledge. Therefore, we survey methods that perform neurosymbolic reasoning tasks on knowledge graphs and propose a novel taxonomy by which we can classify them. Specifically, we propose three major categories: (1) logically-informed embedding approaches, (2) embedding approaches with logical constraints, and (3) rule learning approaches. Alongside the taxonomy, we provide a tabular overview of the approaches and links to their source code, if available, for more direct comparison. Finally, we discuss the unique characteristics and limitations of these methods, then propose several prospective directions toward which this field of research could evolve.

Integrating large language models (LLMs) with knowledge graphs derived from domain-specific data represents an important advancement towards more powerful and factual reasoning. As these models grow more capable, it is crucial to enable them to perform multi-step inferences over real-world knowledge graphs while minimizing hallucination. While large language models excel at conversation and text generation, their ability to reason over domain-specialized graphs of interconnected entities remains limited. For example, can we query a LLM to identify the optimal contact in a professional network for a specific goal, based on relationships and attributes in a private database? The answer is no--such capabilities lie beyond current methods. However, this question underscores a critical technical gap that must be addressed. Many high-value applications in areas such as science, security, and e-commerce rely on proprietary knowledge graphs encoding unique structures, relationships, and logical constraints. We introduce a fine-tuning framework for developing Graph-aligned LAnguage Models (GLaM) that transforms a knowledge graph into an alternate text representation with labeled question-answer pairs. We demonstrate that grounding the models in specific graph-based knowledge expands the models' capacity for structure-based reasoning. Our methodology leverages the large-language model's generative capabilities to create the dataset and proposes an efficient alternate to retrieval-augmented generation styled methods.

Exploring the Potential of AI-Powered Knowledge Graphs with MindGraph ... Have you ever wondered how we can harness the power of AI to create and explore…

Knowledge Discovery and Generation: Synergizing Knowledge Graphs and Large Language Models 💡 In today’s era of information explosion, the volume of… | 14 comments on LinkedIn

Unlocking the Secrets of Scientific Discovery with AI and Knowledge Graphs ... Have you ever wondered how AI could revolutionize the way we conduct scientific… | 17 comments on LinkedIn

Graph Neural Prompting with Large Language Models

🌟GraphGPT🌟 (385 stars in GitHub) is accepted by 🌟SIGIR'24🌟 (only 20.1% acceptance rate)! Thank Yuhao Yang, wei wei, and other co-authors for their precious…

Large language models (LLMs) have achieved great success in many fields, and recent works have studied exploring LLMs for graph discriminative tasks such as node classification. However, the abilities of LLMs for graph generation remain unexplored in the literature. Graph generation requires the LLM to generate graphs with given properties, which has valuable real-world applications such as drug discovery, while tends to be more challenging. In this paper, we propose LLM4GraphGen to explore the ability of LLMs for graph generation with systematical task designs and extensive experiments. Specifically, we propose several tasks tailored with comprehensive experiments to address key questions regarding LLMs' understanding of different graph structure rules, their ability to capture structural type distributions, and their utilization of domain knowledge for property-based graph generation. Our evaluations demonstrate that LLMs, particularly GPT-4, exhibit preliminary abilities in graph generation tasks, including rule-based and distribution-based generation. We also observe that popular prompting methods, such as few-shot and chain-of-thought prompting, do not consistently enhance performance. Besides, LLMs show potential in generating molecules with specific properties. These findings may serve as foundations for designing good LLMs based models for graph generation and provide valuable insights and further research.

InBox: Enhancing Recommender Systems with Knowledge Graph-based Interest Box Embeddings ... 🧠 (Alibaba Group / Ant Group) Imagine if AI could understand not…

G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering

Knowledge engineering is a discipline that focuses on the creation and maintenance of processes that generate and apply knowledge. Traditionally, knowledge engineering approaches have focused on knowledge expressed in formal languages. The emergence of large language models and their capabilities to effectively work with natural language, in its broadest sense, raises questions about the foundations and practice of knowledge engineering. Here, we outline the potential role of LLMs in knowledge engineering, identifying two central directions: 1) creating hybrid neuro-symbolic knowledge systems; and 2) enabling knowledge engineering in natural language. Additionally, we formulate key open research questions to tackle these directions.

How to Combine RAG, Reinforcement Learning, and Knowledge Graphs for More Robust AI Agents ⭕ Recent months have seen rapid progress in developing large…

Knowledge Graphs Achieve Superior Reasoning versus Vector Search alone for Retrieval Augmentation 🔗 As artificial intelligence permeates business… | 29 comments on LinkedIn

Leveraging Graph Algorithms to Enable Responsible AI Reasoning 💡 Large language models have shown immense promise in their ability to generate remarkably…

Leveraging Graphs to Advance Chain-of-Thought Reasoning ⛓ Chain-of-thought (CoT) prompting has rapidly emerged as a technique to substantially improve the…

Injecting KGs in RAG in pre-processing, post-processing, chunk extraction, document and contextual hierarchies, with a concrete example.

Knowledge engineering is a discipline that focuses on the creation and maintenance of processes that generate and apply knowledge. Traditionally, knowledge engineering approaches have focused on knowledge expressed in formal languages. The emergence of large language models and their capabilities to effectively work with natural language, in its broadest sense, raises questions about the foundations and practice of knowledge engineering. Here, we outline the potential role of LLMs in knowledge engineering, identifying two central directions: 1) creating hybrid neuro-symbolic knowledge systems; and 2) enabling knowledge engineering in natural language. Additionally, we formulate key open research questions to tackle these directions.

Orchestrating Efficient Reasoning Over Knowledge Graphs with LLM Compiler Frameworks 🔵 (published in Towards Data Science) Recent innovations in Large…

I really enjoyed the latest #UnconfuseMe with Bill Gates and Yejin Choi.  Yejin's research is on symbolic knowledge distillation, which means they take large…

The advent of large language models (LLMs) , trained on vast amounts of text data, has been one of the most significant breakthroughs in…

Before gearing up for yet another AI project, ask if it's really the best approach.

Investing in Knowledge Graph provides higher accuracy for LLM-powered question-answering systems. And ultimately, to succeed in this AI world, enterprises must… | 23 comments on LinkedIn

A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests

Learn how to get GPT to ask complex questions in any language

Natural language processing made easy