(EACL '24) MultiMUC: Multilingual Template Filling on MUC-4 Draft: openreview.net/forum?id=0qSGR… By William Gantt Shabnam Behzad @hannah0 Yunmo Chen Aaron Steven Benjamin Van Durme Mahsa Yarmohammadi TLDR — The first multilingual parallel corpus for template filling.

Streaming is an interesting topic to investigate. We proposed a simple but effective solution for two timing issues in streams: 1) when there is enough information for the downstream to process; 2) when the buffer should be processed for an optimal memory footprint. Our new work:

📢 Happy to share that our paper on #LLM safety in multilingual contexts has been accepted at #ACL 2024! ✨ We show the difficulty of alleviating multilingual safety issues in LLMs through standard alignment methods. arxiv.org/abs/2401.13136 🧵1/7

🧐Looking for a super-fast 🚀 speech-to-speech translation (S2ST) system while maintaining high-quality 📈generation? Our paper uses ideas from diffusion models to improve S2ST. 💡✨ arXiv link: arxiv.org/abs/2405.13274 Github repo: github.com/steventan0110/… A thread 🧵

Will be presenting my work on LLM-MT at #naacl today, at In-Person Poster Session 7 (11am). Please come if you are interested in machien translation and multilinguality! Would also love to discuss multimodal LLM (speech + text) and non-autoregressive decoding (NAT, diffusion)!

Here’s some better news: Combining CPO and SimPO can likely improve the model! Check out more details in our GitHub code: github.com/fe1ixxu/CPO_SI…

It is an honor to spend the last few years at Hopkins. Really appreciate the help and support from faculties and students there. 👾 thank you!

Low-resource, high-risk: A Johns Hopkins University study (feat. Daniel Khashabi 🕊️, Lingfeng Shen, Weiting (Steven) Tan, Yunmo Chen, Jack Jingyu Zhang, Haoran Xu, & more) finds that #AI text generators are more likely to create harmful content in certain languages. Learn more: bit.ly/3Y6SacA

“Learning to Retrieve Iteratively for In-Context Learning” Yunmo Chen, Tongfei Chen, Harsh Jhamtani,Patrick Xia, Richard Shin, Jason Eisner, Benjamin Van Durme arxiv.org/abs/2406.14739

😉 I’m also at Tech At Bloomberg now.

TBH, I didn’t expect to have another outstanding paper in my Iter* series of paper… really appreciate the recognition of our work and congratulations to my collaborators! 🎉

😕 I would have made my best effort to be there in person for the award if I could have known it in advance…. It looks like me and my collaborators absented from the awards all the time😂