ACLApr, 2024
缓解上下文记忆以提高开放领域问答的泛化能力
Towards Better Generalization in Open-Domain Question Answering by Mitigating Context Memorization
Zixuan Zhang, Revanth Gangi Reddy, Kevin Small, Tong Zhang, Heng Ji
TL;DROpen-domain Question Answering research investigates the generalization performance of a retrieval-augmented QA model, proposing Corpus-Invariant Tuning as an effective training strategy to mitigate knowledge over-memorization and achieve better generalizability.