An extended annotation scheme with new categories and attributes plus a Gemma-300M-based multi-head classifier achieves 81.6% macro F1 on personal fact classification, outperforming few-shot LLM baselines by nearly 9 points with lower compute.
Unifying large language models and knowledge graphs: a roadmap
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Forward replay replaces backward spreading in LLM parameter editing by optimizing the target hidden state at the first editing layer and propagating it forward, yielding more accurate layer-wise targets at the same computational cost.
AF-Retriever delivers state-of-the-art zero- and one-shot results on three STaRK QA benchmarks by using LLM extraction, vector similarity, incremental scope expansion, and hybrid retrieval.
Ontology-grounded tool architectures eliminate hallucination of domain identifiers in industrial AI agents by enforcing semantic constraints through a typed relational configuration and three-operation interface.
GS-Quant generates coarse-to-fine discrete codes for KG entities via semantic hierarchy injection and causal sequence reconstruction, enabling LLMs to perform knowledge graph completion by treating the codes as vocabulary tokens.
BifrostRAG combines dual knowledge graphs with hybrid retrieval to improve multi-hop question answering on construction safety regulations, reporting 87.3% F1 on a custom dataset.
citing papers explorer
-
An Annotation Scheme and Classifier for Personal Facts in Dialogue
An extended annotation scheme with new categories and attributes plus a Gemma-300M-based multi-head classifier achieves 81.6% macro F1 on personal fact classification, outperforming few-shot LLM baselines by nearly 9 points with lower compute.
-
From Backward Spreading to Forward Replay: Revisiting Target Construction in LLM Parameter Editing
Forward replay replaces backward spreading in LLM parameter editing by optimizing the target hidden state at the first editing layer and propagating it forward, yielding more accurate layer-wise targets at the same computational cost.
-
Autofocus Retrieval: An Effective Pipeline for Multi-Hop Question Answering With Semi-Structured Knowledge
AF-Retriever delivers state-of-the-art zero- and one-shot results on three STaRK QA benchmarks by using LLM extraction, vector similarity, incremental scope expansion, and hybrid retrieval.
-
The Semantic Training Gap: Ontology-Grounded Tool Architectures for Industrial AI Agent Systems
Ontology-grounded tool architectures eliminate hallucination of domain identifiers in industrial AI agents by enforcing semantic constraints through a typed relational configuration and three-operation interface.
-
GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion
GS-Quant generates coarse-to-fine discrete codes for KG entities via semantic hierarchy injection and causal sequence reconstruction, enabling LLMs to perform knowledge graph completion by treating the codes as vocabulary tokens.
-
Bridging Dual Knowledge Graphs for Multi-Hop Question Answering in Construction Safety
BifrostRAG combines dual knowledge graphs with hybrid retrieval to improve multi-hop question answering on construction safety regulations, reporting 87.3% F1 on a custom dataset.
- GraphMind: From Operational Traces to Self-Evolving Workflow Automation