AI RESEARCH
Gradually Excavating External Knowledge for Implicit Complex Question Answering
arXiv CS.CL
•
ArXi:2603.08148v1 Announce Type: new Recently, large language models (LLMs) have gained much attention for the emergence of human-comparable capabilities and huge potential. However, for open-domain implicit question-answering problems, LLMs may not be the ultimate solution due to the reasons of: 1) uncovered or out-of-date domain knowledge, 2) one-shot generation and hence restricted comprehensiveness.