The largest workshop on analysing and interpreting neural networks for NLP.
BlackboxNLP will be held at EMNLP 2025 in Suzhou, China
blackboxnlp.github.io
BlackboxNLP
Loading...
📣 Announcing the BlackboxNLP 2026 Reproducibility Challenge!
A new track dedicated to rigorous robustness checks of NLP interpretability work - stress-testing baselines, ablations, generalizability, and evaluation.
Interested? Submit a short Expression of Interest naming the paper you'd like to revisit and which theme(s) you'll target. It helps us coordinate efforts and avoid overlap across teams.
🔗 blackboxnlp.github.io/2026/reprodu...
📝 EoI form: forms.gle/gn2auMLagc6k...
Inspired by similar efforts like the ML Reproducibility Challenge, we invite the community to revisit and enrich recent interpretability papers - not to question their validity, but to clarify where findings hold, where they break, and what truly drives the reported findings.
BlackboxNLP will be co-located with EMNLP 2026 in 🇭🇺 Budapest 🇭🇺 this October!
This edition will feature a special reproducibility track, investigating generalization and robustness of established results from interpretability research 👷♂️
Stay tuned for more details!
🔗 Check out our website for details, updates, and important dates:
blackboxnlp.github.io/2026/
BlackboxNLP is back once again at EMNLP'26! Very happy to be part of the team again, and excited for our new reproducibility track! Check it out ⬇️
