A new benchmark, KnowShiftQA, shows that retrieval-augmented LLMs drop 22 to 27 points in accuracy when textbook facts are hypothetically updated to conflict with the model's parametric knowledge.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
KnowShiftQA: How Robust are RAG Systems when Textbook Knowledge Shifts in K-12 Education?
A new benchmark, KnowShiftQA, shows that retrieval-augmented LLMs drop 22 to 27 points in accuracy when textbook facts are hypothetically updated to conflict with the model's parametric knowledge.