Must-read papers on knowledge graph reasoning
-
Updated
Apr 16, 2021
Must-read papers on knowledge graph reasoning
The official implementation of ICLR 2020, "Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering".
Multi-hop knowledge graph reasoning learned via policy gradient with reward shaping and action dropout
VeritasGraph: Enterprise-Grade Graph RAG for Secure, On-Premise AI with Verifiable Attribution
Mimir - Fully open and customizable memory bank with semantic vector search capabilities for locally indexed files (Code Intelligence) and stored memories that are shared across sessions and chat contexts allowing worker agent to learn from errors in past runs. Includes Drag and Drop multi-agent orchestration
Source codes and datasets for EMNLP 2020 paper "Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph"
EMNLP 22' (Oral): SQUIRE: A Sequence-to-sequence Framework for Multi-hop Knowledge Graph Reasoning
[AAAI 2023] Official resources of "NQE: N-ary Query Embedding for Complex Query Answering over Hyper-relational Knowledge Graphs".
This is the code for the MLRC2020 challenge w.r.t. the ACL 2020 paper Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings
Discover advanced AI techniques in my repository combining Multi-Hop Chain of Thought (CoT) and Retrieval-Augmented Generation (RAG) using DSPy and Indexify. Enhance complex problem-solving with multi-step reasoning and external knowledge integration. Perfect for AI enthusiasts and researchers.
[ACL'2024 Findings] "Understanding and Patching Compositional Reasoning in LLMs"
Code and data for the AAAI 2022 paper "Hybrid Autoregressive Inference for Scalable Multi-hop Explanation Regeneration"
Code for the EACL 2021 paper "Unification-based Reconstruction of Multi-hop Explanations for Science Questions"
Stanford CS224N Final Project. A text-based multi-hop reasoning question-answer NLP model to address the research question: "What if language models could ask their own questions?"
CrawlLama 🦙 is an local AI agent that answers questions via Ollama and integrates web- and RAG-based research.
Anti-faCtual COmmonsense Reasoning Disentanglement
Shared Task for the COLING 2020 conference
Add a description, image, and links to the multi-hop-reasoning topic page so that developers can more easily learn about it.
To associate your repository with the multi-hop-reasoning topic, visit your repo's landing page and select "manage topics."