6 papers
Few-Shot Multilingual Open-Domain QA from 5 Examples
Fan Jiang, Tom Drummond, Trevor Cohn
Recent approaches to multilingual open-domain question answering (MLODQA) have achieved promising results given abundant language-specific training data. However, the considerable…
Franken-Adapter: Cross-Lingual Adaptation of LLMs by Embedding Surgery
Fan Jiang, Honglin Yu, Grace Chung +1
The capabilities of Large Language Models (LLMs) in low-resource languages lag far behind those in English, making their universal accessibility a significant challenge. To allevia…
Pre-training Cross-lingual Open Domain Question Answering with Large-scale Synthetic Supervision
Fan Jiang, Tom Drummond, Trevor Cohn
Cross-lingual open domain question answering (CLQA) is a complex problem, comprising cross-lingual retrieval from a multilingual knowledge base, followed by answer generation in th…
Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval
Fan Jiang, Qiongkai Xu, Tom Drummond +1
Neural 'dense' retrieval models are state of the art for many datasets, however these models often exhibit limited domain transfer ability. Existing approaches to adaptation are un…
Noisy Self-Training with Synthetic Queries for Dense Retrieval
Fan Jiang, Tom Drummond, Trevor Cohn
Although existing neural retrieval models reveal promising results when training data is abundant and the performance keeps improving as training data increases, collecting high-qu…
Fingerprint Attack: Client De-Anonymization in Federated Learning
Qiongkai Xu, Trevor Cohn, Olga Ohrimenko
Federated Learning allows collaborative training without data sharing in settings where participants do not trust the central server and one another. Privacy can be further improve…