BlackboxNLP will be co-located with #EMNLP2025 in Suzhou this November! 📷This edition will feature a new shared task on circuits/causal variable localization in LMs, details: blackboxnlp.github.io/2025/t…
If you're into mech interp and care about evaluation, please submit!
Excited to announce this year's best paper award: 🏆 "Language Dominance in Multilingual Large Language Models" by Nadav Shani and Ali Basirat 🏆
This paper challenges a common conception that multilingual models perform computation via a dominant language.
Congratulations!
I am recruiting 2 PhD students to work on LM interpretability at UMD @umdcs starting in fall 2026!
We are #3 in AI and #4 in NLP research on @CSrankings.
Come join us in our lovely building just a few miles from Washington, D.C. Details in 🧵
Presenting a poster today at #BlackboxNLP? You are welcome to present in either poster session, or both! See the full program on our website: blackboxnlp.github.io/2025/
Very honored to be one out of seven outstanding papers at this years' EMNLP :)
Huge thanks to my amazing collaborators @fatemehc__@anmarasovic@boknilev, this would not have been possible without them!
Very honored to be one out of seven outstanding papers at this years' EMNLP :)
Huge thanks to my amazing collaborators @fatemehc__@anmarasovic@boknilev, this would not have been possible without them!
Had great visits at @MITCS, @KempnerInst , and @BrownUniversity (+ @celtics)!
Now heading to #EMNLP to present 3 papers:
1️⃣ "Trust Me, I'm Wrong"
2️⃣ Our part in a new multilingual PIQA-style dataset
3️⃣ Our shared-task submission at @BlackboxNLP!
Come say hi and let’s chat!
On the one hand, oh dear. On the other hand, thank you for being open about this @percyliang and the team. Who knows how frequent that kind of leak is.
Digging into this, we realized to our horror that we had actually trained on the GSM8K test set. 😱 Due some comedy of errors, we had trained on a version with the wrong formatting, so that made our GSM8K numbers exceptionally bad instead of exceptionally good.🤔
LLMs can hallucinate due to different reasons:
❌They don't know (lack of knowledge)
❌ They "know" but are uncertain
❌They "know" and are certain
New Extended version of our paper that combines our understanding of hallucination on the knowledge and certainty axis is out🧵
Q: which of these can be checked by an LLM as well as an overly loaded human reviewer?
Appropriateness
Formatting
Length
Anonymity
Limitations
Responsible Checklist
Potential Violation Justification
Need Ethics Review
Ethics Review Justification
aclrollingreview.org/reviewe…
.@Cornell is recruiting for multiple postdoctoral positions in AI as part of two programs: Empire AI Fellows and Foundational AI Fellows. Positions are available in NYC and Ithaca.
Deadline for full consideration is Nov 20, 2025!
academicjobsonline.org/ajo/j…