We wrap up today with a panel on (mechanistic) interpretability, joined by John Hewitt (John Hewitt), Zhijing Jin (@ZhijingJin), Antoine Bosselut (@ABosselut), and Neel Nanda (@NeelNanda5)!

Now at BlackboxNLP: Emmanuele Chersoni giving a linguistically motivated talk on Event Construal in BERT!

surprisingly well attended room at 9am

We're on our way with an invited talk by Zhijing Jin in the West Ballroom 2!

Only 2 more days until BlackboxNLP gets started! Have a look at the schedule, it's filled to the brim with exciting interpretability research🤩

blackboxnlp.github.io

The submission deadline for BlackboxNLP is approaching, September 1st!

Unhappy with your EMNLP reviews and working on interpretability-related topics? Why not submit to BlackboxNLP instead?

blackboxnlp.github.io

Want to discuss evaluation in #nlproc interpretability? Consider submitting to the #blackboxNLP workshop.

Deadline: September 1
blackboxnlp.github.io
Follow BlackboxNLP

Working on interpretability? Trying to gain a better insight into *how* a model came to a prediction?
Consider submitting to BlackboxNLP!

Submission deadline: Sep 1
Workshop date: Dec 7 @ EMNLP

We also accept work-in-progress in a non-archival track!

blackboxnlp.github.io

BlackboxNLP, the workshop on interpretability and analysis of NLP, will be held at EMNLP 2023 this year, December 7! 🎉 We're calling for all work that attempts to better understand the inner workings of neural models, with a deadline on September 1st!

blackboxnlp.github.io