Decoding on Graphs: Empower LLMs with KGs (MIT)
Decoding on Graphs (DoG) is a novel framework that integrates Large Language Models (LLMs) with Knowledge Graphs (KGs) to enhance question-answering (QA) tasks. The key innovation is the concept of a "well-formed chain", a sequence of interconnected fact triplets from the KG that starts with entities mentioned in the question and leads logically to the answer. To ensure that LLMs generate these chains faithfully, DoG introduces graph-aware constrained decoding, which dynamically restricts the LLM's token generation based on the KG's topology. This is achieved using a trie data structure that maintains valid token sequences corresponding to the KG's paths, ensuring that each generated reasoning step aligns with actual KG relations and entities. Additionally, DoG employs beam search execution at the triplet level to explore multiple plausible reasoning paths simultaneously, enhancing the robustness and accuracy of the answers. By constraining the LLM's decoding process without altering its underlying parameters or requiring additional training, DoG effectively leverages the LLM's inherent reasoning capabilities while grounding its outputs in the structured knowledge of the KG. Experimental results demonstrate that DoG outperforms existing methods on several KGQA benchmarks, particularly in complex multi-hop reasoning scenarios, highlighting its effectiveness and adaptability across different KGs and LLMs. all rights w/ authors: Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains https://arxiv.org/pdf/2410.18415 Nice Idea by @mit and Univ of Hong Kong 00:00 Augment LLMs with Knowledge Graphs 00:47 Subgraph retrievers 02:03 Agents for Integrating LLM and KG 04:25 NEW IDEA by MIT & HK Univ 08:33 Example of Decode on Graphs 15:21 Implementation PROMPT DoG 17:20 Linear graph forms 19:43 Graph aware constrained decoding 24:20 Harvard MED Agents for LLM on KG #aiagents #airesearch #artificialintelligence #massachusettsinstituteoftechnology

AI Agents for Smarter Data Input: DocETL (Berkeley)

Knowledge Graph or Vector Database… Which is Better?
![Yann LeCun's $1B Bet Against LLMs [Part 1]](https://i.ytimg.com/vi/kYkIdXwW2AE/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLDbV4izF3i-wxevCVIn7FJjoy1vlA)
Yann LeCun's $1B Bet Against LLMs [Part 1]

Big Techday 26: Reap the experts: LLM compression and edge deployment - Sherif Cherfa, 0xSero

Visualizing transformers and attention | Talk for TNG Big Tech Day '24

Large Language Models and Knowledge Graphs: Merging Flexibility and Structure

An Introduction to Graph Neural Networks: Models and Applications

Is RAG Still Needed? Choosing the Best Approach for LLMs

GraphRAG: The Marriage of Knowledge Graphs and RAG: Emil Eifrem

Don't learn AI Agents without Learning these Fundamentals

START YOUR TUESDAY WITH FAITH | TODAY GOD IS GIVING YOU UNEXPECTED OPPORTUNITIES | FATHER FREDDY ...

It's Not About Scale, It's About Abstraction

Inside Anthropic, the $965 Billion AI Juggernaut | The Circuit

How to build Multimodal Retrieval-Augmented Generation (RAG) with Gemini

GraphGeeks Talk Ep8: How To Create Knowledge Graphs from Unstructured Data

Training Sand to Think: Artificial General Intelligence & Future of Physics

Smart LLM Routing & Novel Multi-Agent Framework

AI "Behavior Cloning" for fast Residual RL (MIT, Harvard)

Unleashing the Synergy of LLMs and Knowledge Graphs

