On memorized question-answer pairs from KMIR and NQ, bottleneck and prefix adapters trained on entity-swapped contexts let a GPT-2 reader follow the new context most of the time, though no baselines are reported.
Extracting training data from large language models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Mitigating Knowledge Conflicts in Language Model-Driven Question Answering
On memorized question-answer pairs from KMIR and NQ, bottleneck and prefix adapters trained on entity-swapped contexts let a GPT-2 reader follow the new context most of the time, though no baselines are reported.