repoGitHubTrust 82 · PrimaryPublished 1mo agoLive · 27d ago
douglasjordan2/c0
An external memory for LLMs: a bi-temporal knowledge graph with hybrid (keyword + vector) retrieval and a self-improving reflection loop. Benchmarked to beat flat vector RAG on corrections and time-versioned queries.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 54%Grounding LLM Reasoning under Incomplete Graph Evidence →
- PossiblePossibly related (embedding) · 53%AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents →
- PossiblePossibly related (embedding) · 52%Efficient Retrieval-Augmented Generation via Token Co-occurrence Graphs →
- PossiblePossibly related (embedding) · 51%Forecasting With LLMs: Improved Generalization Through Feature Steering →
- PossiblePossibly related (embedding) · 51%Query-Aware Spreading Activation for Multi-Hop Retrieval over Knowledge Graphs →
- PossiblePossibly related (embedding) · 48%DynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented Generation →
- PossiblePossibly related (embedding) · 52%Data Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data Complexities →
- PossiblePossibly related (embedding) · 49%RSF-GLLM: Bridging the Semantic Gap in Multi-Hop Knowledge Graph QA via Recurrent Soft-Flow and Decoupled LLM Generation →
Implements
paperGrounding LLM Reasoning under Incomplete Graph EvidencepaperAgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM AgentspaperEfficient Retrieval-Augmented Generation via Token Co-occurrence GraphspaperForecasting With LLMs: Improved Generalization Through Feature SteeringpaperQuery-Aware Spreading Activation for Multi-Hop Retrieval over Knowledge Graphs
Implements (incoming)
paperDynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented GenerationpaperData Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data ComplexitiespaperRSF-GLLM: Bridging the Semantic Gap in Multi-Hop Knowledge Graph QA via Recurrent Soft-Flow and Decoupled LLM GenerationpaperTowards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model FinetuningpaperEvoGraph-R1: Self-Evolving Multimodal Knowledge Hypergraphs for Agentic RetrievalpaperExtractable Memorization From First Principles
Covers (incoming)
Related across the graph
paperDynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented GenerationpaperAgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM AgentspaperTowards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model FinetuningpaperGrounding LLM Reasoning under Incomplete Graph EvidencenewsCan LLMs Perform Deep Technical Comprehension of Computer Architecture PaperspaperRSF-GLLM: Bridging the Semantic Gap in Multi-Hop Knowledge Graph QA via Recurrent Soft-Flow and Decoupled LLM GenerationpaperEfficient Retrieval-Augmented Generation via Token Co-occurrence GraphspaperQuery-Aware Spreading Activation for Multi-Hop Retrieval over Knowledge GraphspaperExtractable Memorization From First PrinciplespaperEvoGraph-R1: Self-Evolving Multimodal Knowledge Hypergraphs for Agentic RetrievalpaperData Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data ComplexitiespaperForecasting With LLMs: Improved Generalization Through Feature Steering
