all AI news
Data Distribution Bottlenecks in Grounding Language Models to Knowledge Bases. (arXiv:2309.08345v2 [cs.CL] UPDATED)
cs.CL updates on arXiv.org arxiv.org
Language models (LMs) have already demonstrated remarkable abilities in
understanding and generating both natural and formal language. Despite these
advances, their integration with real-world environments such as large-scale
knowledge bases (KBs) remains an underdeveloped area, affecting applications
such as semantic parsing and indulging in "hallucinated" information. This
paper is an experimental investigation aimed at uncovering the robustness
challenges that LMs encounter when tasked with knowledge base question
answering (KBQA). The investigation covers scenarios with inconsistent data
distribution between training and …
advances applications arxiv bottlenecks cs.cl data distribution environments information integration knowledge language language models lms natural parsing scale semantic understanding world