RT @EmmanueleChers1: I am happy to announce that our paper "Log probabilities are a reliable estimate of semantic plausibility in base and…

We wrap up the day with a panel on the state of interpretability with 4 fantastic panellists: @jack_merullo_, @_dieuwke_, @mariusmosbach and @QVeraLiao!

@hima_lakkaraju @lieberum_t @sarahwiegreffe wrapping up the oral session with a presentation of "Mechanistic?"

Now continuing with Emmanuele Chersoni presenting "Log Probabilities Are a Reliable Estimate of Semantic Plausibility in Base and Instruction-Tuned Language Models"

BlackboxNLP has started with our first keynote by Jack Merullo! Come join us in the Jasmine room to learn about his talk on "Simple Mechanisms Underlying Complex Behaviors in Language Models".

During BlackboxNLP we will hold a panel discussion on the state of interpretability in NLP. We are soliciting questions for this now, so if there is any topic you think would be interesting to discuss: this is your chance!

BlackboxNLP welcomes EMNLP Findings papers for (poster) presentation at our workshop! If you have a Findings paper on an interpretability-related topic, consider presenting it at BlackboxNLP! Please register your paper here, before October 28:

All accepted papers for BlackboxNLP 2024 can be found here: Congratulations to all authors on their fine work! 🎉

We have extended the submission deadline to *August 19*, AoE time! Furthermore, we have also opened a commitment link for ARR-reviewed papers. This allows you to submit to BlackboxNLP directly without additional reviews:

The submission deadline (15 aug) for BlackboxNLP is slowly approaching! We're very excited to see your approaches to open up the black box 🤩 The submission portal has now been opened on OpenReview:

For more info have a look at our website!

🎖️ On Quick Kisses and How to Make Them Count: A Study on Event Construal in Light Verb Constructions with BERT by Chenxin Liu and Emmanuele Chersoni