2 papers
cs.CL2026
MARS: Multi-hop Adaptive Retrieval and SPARQL Generation for KGQA
Nikit Srivastava, Daniel Vollmers, René Speck +3
Large language models (LLMs) have demonstrated strong reasoning performance, but their tendency to hallucinate limits their reliability in knowledge-intensive tasks requiring up-to…
cs.CL2017
BENGAL: An Automatic Benchmark Generator for Entity Recognition and Linking
Axel-Cyrille Ngonga Ngomo, Michael Röder, Diego Moussallem +2
The manual creation of gold standards for named entity recognition and entity linking is time- and resource-intensive. Moreover, recent works show that such gold standards contain…