KGQA
PulseAugur coverage of KGQA — every cluster mentioning KGQA across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Hugging Face paper reveals "token collapse" in LLM graph prompting
A new paper from Hugging Face Daily Papers investigates the phenomenon of "token collapse" in graph soft prompting for large language models. This issue occurs when learned graph tokens become indistinguishable, functio…
-
New framework uses LLMs to bridge semantic gap in knowledge graph reasoning
Researchers have developed a new framework called Enrich-on-Graph (EoG) to improve the reasoning capabilities of Large Language Models (LLMs) in knowledge-intensive tasks like knowledge graph question answering (KGQA). …
-
New benchmark evaluates LLMs for geospatiotemporal power outage analysis
Researchers have introduced GeoOutageBench, a new benchmark designed to evaluate Large Language Models (LLMs) in their ability to perform geospatiotemporal Knowledge Graph Question Answering (KGQA) for analyzing power o…
-
New research pinpoints subgraph construction as key failure point in GNN-based KGQA
Researchers have identified that the subgraph construction stage, not the GNN reasoning stage, is the primary cause of failure in graph neural network-based Knowledge Graph Question Answering (KGQA) pipelines when subje…
-
New framework MissDiag evaluates KGQA and KG-RAG robustness to missing knowledge
Researchers have introduced MissDiag, a new framework designed to evaluate the robustness of knowledge graph question answering (KGQA) and knowledge-graph-based retrieval-augmented generation (KG-RAG) systems when faced…
-
New KG2Code method bridges knowledge graphs and LLMs via executable code
Researchers have introduced KG2Code, a novel method that converts knowledge graphs into an executable code format. This approach aims to improve knowledge graph question answering (KGQA) by leveraging the code-awareness…
-
MARS system integrates LLMs with knowledge graphs for KGQA without fine-tuning
Researchers have developed MARS, a novel approach for knowledge graph question answering (KGQA) that integrates large language models (LLMs) with knowledge graphs (KGs) without requiring model fine-tuning. MARS employs …