Internet-augmented language models through few-shot prompting for open-domain question answering (2022 · 209 citations)
Large language models often state wrong facts, either because they recall knowledge badly or because their training data is old or incomplete.
Better Document-Level Machine Translation with Bayes' Rule (2020 · 72 citations)
Translating whole documents requires cross-sentence context. For example, Chinese marks tense and number less explicitly than English, so the right English form often depends on other sentences. However, parallel documents for training are scarce. The authors address this by applying Bayes' rule, the classic noisy…

All works

4 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

Gemma: Open Models Based on Gemini Research and Technology ↗arXiv:2403.08295 · no summary yetGemma Team et al.2024 · 1,313 citations
Internet-augmented language models through few-shot prompting for open-domain question answeringarXiv:2203.05115Angeliki Lazaridou, Elena Gribovskaya, Wojciech Stokowiec, et al.2022 · 209 citations
Better Document-Level Machine Translation with Bayes' RuleTransactions of the Association for Computational Linguistics (TACL)Lei Yu, Laurent Sartran, Wojciech Stokowiec, et al.2020 · 72 citations
Enabling arbitrary translation objectives with Adaptive Tree Search ↗arXiv:2202.11444 · no summary yetWang Ling et al.2022

Co-authors here

7 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 4,766 times (of the 149,439 papers whose bibliographies we read); 890 citing papers with a page here →.

Updated 31 October 2026