John Wieting
@johnwieting2
Senior Research Scientist @GoogleDeepMind 🧠. PhD @LTIatCMU.
Congratulations to UMD!
.@UofMaryland's CS dept is welcoming eight new tenure-track faculty members! With expertise in cutting-edge areas, they'll boost our academic & research capabilities. Welcome aboard! 🐢📚 Read more: go.umd.edu/Hires24
Is it possible to have a watermark that reliably detects LLM-generated text, is robust to paraphrasing attacks, preserves quality, and can be applied to any LLM without access to logits? Check out PostMark, a method with all these properties! arxiv.org/abs/2406.14517 🧵below:
Excited to share that SWIM-IR has been accepted at #NAACL2024! 🍻 I'm quite delighted with this work as it was completed during my internship at @GoogleAI! Thanks to all my mentors and colleagues! ❤️ Time to celebrate and hopefully see you all in Mexico! 🇲🇽 🏖️
📢New paper: we release SWIM-IR, a large-scale synthetic multilingual retrieval dataset with 28 million training pairs over 33 languages. 🔥We can improve multilingual retrievers without expensive human-labeled training data. 📜arxiv.org/abs/2311.05800 🦢github.com/google-researc…
There are so many accounts (bots?) on X/Twitter posting ChatGPTish responses or the same irrelevant responses across posts. It seems fairly obvious how these could be filtered out. I wonder why nothing is done. I thought it'd improve over time, but it really hasn't.
ACL announcement: "The ACL Executive Committee has voted to significantly change ACL's approach to protecting anonymous peer review. The change is effective immediately. (1/4) #NLPRoc
Excited to be presenting our work on **Evaluating and Modeling Attribution for Cross-Lingual Question Answering** at #EMNLP2023 in Singapore. Updated Paper: arxiv.org/abs/2305.14332 We're also releasing the XOR-AttriQA dataset: github.com/google-researc… 🧵
Despite the fantastic progress we've seen recently in cross-lingual modeling, the best systems still make a lot of factual errors. To address this, here is our work on 🚨 Evaluating and Modeling Attribution for Cross-Lingual Question Answering 🚨 #1 Attribution Evaluation: Our…
Later today: Sam Altman: "I'm pleased to announce I'm looking to raise venture capital for my new startup: ClosedAI."
Can LLMs generate exact 5 words? No How about 5 sentences? No How about 5 paragraphs? No 🤷🏻♀️ In arxiv.org/abs/2310.14542, we evaluate the performance of LLMs on various controlled generation tasks including numerical planning, story generation, paraphrase generation, and etc. (1/n)