🏆 Announcing the NDIF Best Paper Award for the BlackboxNLP 2026 Reproducibility Challenge! @ndif-team.bsky.social Reproduce an interp. finding with nnsight + NDIF, open-source it, and push it further. Winners will receive a $500 prize, and will be invited to present at the workshop!

Are you wondering if LLM interpretability results generalize, reproduce, etc.? Check out the reproducibility challenge and submit your work reproducing papers in this area: bsky.app/profile/blac...

BlackboxNLP@blackboxnlp.bsky.social · 2mo ago

📣 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.

📣 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.

How does an LLM’s past influence its future?🤔 In new work, led by @adisimhi.bsky.social, together with @fbarez.bsky.social @boknilev.bsky.social and Shay Cohen, we find conversational history creates a latent "geometric trap" which makes old habits e.g. hallucinations hard to break!

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!

🤔What happens when LLM agents choose between achieving their goals and avoiding harm to humans in realistic management scenarios? Are LLMs pragmatic or prefer to avoid human harm? 🚀 New paper out: ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs🚀🧵

Traveling to #COLM2025 this week, and here's some work from our group and collaborators: Cognitive biases, hidden knowledge, CoT faithfulness, model editing, and LM4Science See the thread for details and reach out if you'd like to discuss more!

What's the right unit of analysis for understanding LLM internals? We explore in our mech interp survey (a major update from our 2024 ms). We’ve added more recent work and more immediately actionable directions for future work. Now published in Computational Linguistics!

Opportunities to join my group in fall 2026: * PhD applications direct or via ELLIS @ellis.eu (ellis.eu/news/ellis-p...) * Post-doc applications direct or via Azrieli (azrielifoundation.org/fellows/inte...) or Zuckerman (zuckermanstem.org/ourprograms/...)

Excited to join @KempnerInst this year! Get in touch if you're in the Boston area and want to chat about anything related to AI interpretability, robustness, interventions, safety, multi-modality, protein/DNA LMs, new architectures, multi-agent communication, or anything else you're excited about!

Kempner Institute at Harvard University@kempnerinstitute.bsky.social · 11mo ago

News from the #KempnerInstitute! We’re thrilled to welcome Yonatan Belinkov (expert in #NLP) and Daphna Weinshall (expert in human & machine vision) as visiting scholars for the 2025–26 academic year. 📖 Read more: bit.ly/47QkDID #AI #MachineVision @boknilev.bsky.social

@robinjia.bsky.social speaking at @kempnerinstitute.bsky.social on Auditing, Dissecting, and Evaluating LLMs

Thrilled that FUR was accepted to @emnlpmeeting.bsky.social Main🎉 In case you can’t wait so long to hear about it in person, it will also be presented as an oral at @interplay-workshop.bsky.social @colmweb.org 🥳 FUR is a parametric test assessing whether CoTs faithfully verbalize latent reasoning.

Martin Tutek@mtutek.bsky.social · last yr.

🚨🚨 New preprint 🚨🚨 Ever wonder whether verbalized CoTs correspond to the internal reasoning process of the model? We propose a novel parametric faithfulness approach, which erases information contained in CoT steps from the model parameters to assess CoT faithfulness. arxiv.org/abs/2502.14829

BlackboxNLP is the workshop on interpreting and analyzing NLP models (including LLMs, VLMs, etc). We accept full (archival) papers and extended abstracts. The workshop is highly attended and is a great exposure for your finished work or feedback on work in progress. #emnlp2025 at Sujhou, China!

BlackboxNLP@blackboxnlp.bsky.social · 12mo ago

📢 Call for Papers! 📢 #BlackboxNLP 2025 invites the submission of archival and non-archival papers on interpreting and explaining NLP models. 📅 Deadlines: Aug 15 (direct submissions), Sept 5 (ARR commitment) 🔗 More details: blackboxnlp.github.io/2025/call/

Join our Discord for discussions and a bunch of simple submission ideas you can try! discord.gg/n5uwjQcxPR Participants will have the option to write a system description paper that gets published.

BlackboxNLP@blackboxnlp.bsky.social · last yr.

⏳ Three weeks left! Submit your work to the MIB Shared Task at #BlackboxNLP, co-located with @emnlpmeeting.bsky.social Whether you're working on circuit discovery or causal variable localization, this is your chance to benchmark your method in a rigorous setup!

Have you started working on your submission for the MIB shared task yet? Tell us what you’re exploring! New featurization methods? Circuit pruning? Better feature attribution? We'd love to hear about it 👇

Working on feature attribution, circuit discovery, feature alignment, or sparse coding? Consider submitting your work to the MIB Shared Task, part of this year’s #BlackboxNLP We welcome submissions of both existing methods and new or experimental POCs!

VLMs perform better on questions about text than when answering the same questions about images - but why? and how can we fix it? In a new project led by Yaniv (@YNikankin on the other app), we investigate this gap from an mechanistic perspective, and use our findings to close a third of it! 🧵

Tried steering with SAEs and found that not all features behave as expected? Check out our new preprint - "SAEs Are Good for Steering - If You Select the Right Features" 🧵

🚨New paper at #ACL2025 Findings! REVS: Unlearning Sensitive Information in LMs via Rank Editing in the Vocabulary Space. LMs memorize and leak sensitive data—emails, SSNs, URLs from their training. We propose a surgical method to unlearn it. 🧵👇w/ @boknilev.bsky.social @mtutek.bsky.social 1/8

Interested in mechanistic interpretability and care about evaluation? Please consider submitting to our shared task at #blackboxNLP this year!

BlackboxNLP@blackboxnlp.bsky.social · last yr.

BlackboxNLP, the leading workshop on interpretability and analysis of language models, will be co-located with EMNLP 2025 in Suzhou this November! 📆 This edition will feature a new shared task on circuits/causal variable localization in LMs, details here: blackboxnlp.github.io/2025/task

Slides available here: docs.google.com/presentation...

Repl4NLP Keynote – Ana Marasovic

If You Want Reasoning, Look Inside Ana Marasović Repl4NLP 2025

docs.google.com

Ana Marasović@anamarasovic.bsky.social · last yr.

I'm late to the NAACL party, but I've just arrived in Albuquerque! I'll talk about measuring faithfulness of verbalized reasoning on *Sunday* at Repl4NLP at *9:45*.

Excited about the release of MIB, a mechanistic Interpretability benchmark! Come talk to us at #iclr2025 and consider submitting to the leaderboard. We’re also planning a shared task around it at #blackboxNLP this year, located with #emnlp2025

Aaron Mueller@amuuueller.bsky.social · last yr.

Lots of progress in mech interp (MI) lately! But how can we measure when new mech interp methods yield real improvements over prior work? We propose 😎 𝗠𝗜𝗕: a 𝗠echanistic 𝗜nterpretability 𝗕enchmark!

We release many public resources, including: 🌐 Website: mib-bench.github.io 📄 Data: huggingface.co/collections/... 💻 Code: github.com/aaronmueller... 📊 Leaderboard: Coming very soon!

1/13 LLM circuits tell us where the computation happens inside the model—but the computation varies by token position, a key detail often ignored! We propose a method to automatically find position-aware circuits, improving faithfulness while keeping circuits compact. 🧵👇

If erasing information from CoT steps adversely affects the prediction of the model, indicating that such explanations are parametrically faithful.

It has been amazing to work with @fatemehc.bsky.social, @anamarasovic.bsky.social and Yonatan Belinkov on this incredibly important topic. I look forward to further works on the parametric faithfulness route! Codebase (& data): github.com/technion-cs-...

GitHub - technion-cs-nlp/parametric-faithfulness

Contribute to technion-cs-nlp/parametric-faithfulness development by creating an account on GitHub.

github.com

🚨New arXiv preprint!🚨 LLMs can hallucinate - but did you know they can do so with high certainty even when they know the correct answer? 🤯 We find those hallucinations in our latest work with @itay-itzhak.bsky.social, @fbarez.bsky.social, @gabistanovsky.bsky.social and Yonatan Belinkov

Sentences are partially understood before they're fully read. How do LMs incrementally interpret their inputs? In a new paper, @amuuueller.bsky.social and I use mech interp tools to study how LMs process structurally ambiguous sentences. We show LMs rely on both syntactic & spurious features! 1/10