Is an LM that acts Bayesian also Bayesian inside? ☝️ Only as far as its beliefs allow! Fine-tuned on an optimal Bayesian model, LMs hold and use better beliefs than usual fine-tuning on golden answers. Details 👇 or bayeslm.github.io #interpretability #nlproc (1/🧵)

It was a pleasure to 🍸

MilaNLP Lab@milanlp.bsky.social · 5mo ago

We had the pleasure of hosting @tresiwald.bsky.social and Alireza Salemi at our latest seminar. Andreas spoke about the reliability of language models through computational argumentation, while Alireza presented his work on personalizing LLMs. Thank you both for the inspiring talks! #NLProc

Do instructions affect how LMs process and produce language? ☝️Not the way you think! 😲LMs barely change task information when processing a task sample. Instead, instructions shape how this information is accessed and expressed when producing output tokens. #interpretability #nlproc (1/🧵)

I already presented some work on reference (names, pronouns, coreference resolution, pronoun fidelity, etc.) as a rich site to evaluate biases and commonsense reasoning, and our work on disentangling model behaviour and internals through aligned probing (led by @tresiwald.bsky.social).

Excited to present this work together with @dippedrusk.com at #EACL. Join us in the poster session 1 (11:30-13:00) 🔥

Andreas Waldis@tresiwald.bsky.social · 9mo ago

LMs that "know more" about toxicity are less toxic! Our #TACL 📄 connects behavior and internals: 💠 LMs amplify toxicity beyond humans 💠 Information about toxicity peaks in lower layers 💠 Bypassing these layers increases toxicity More details👇 #NLProc #interpretability (1/🧵)

Thanks a lot to everyone for the support, guidance, mentoring, collaboration, and great moments over the past years! 🙏 Without you, this journey wouldn't have been such a pleasure — and now excited to see what the future brings! 🚀

UKP Lab@ukplab.bsky.social · 8mo ago

🎓 𝗣𝗵𝗗 𝗱𝗲𝗳𝗲𝗻𝘀𝗲 𝗰𝗼𝗻𝗴𝗿𝗮𝘁𝘂𝗹𝗮𝘁𝗶𝗼𝗻𝘀 𝘁𝗼 𝗔𝗻𝗱𝗿𝗲𝗮𝘀 𝗪𝗮𝗹𝗱𝗶𝘀! Congratulations to @tresiwald.bsky.social on the successful defense of his dissertation “𝘈𝘯 𝘐𝘯𝘵𝘦𝘨𝘳𝘢𝘭 𝘝𝘪𝘦𝘸 𝘰𝘯 𝘵𝘩𝘦 𝘙𝘦𝘭𝘪𝘢𝘣𝘪𝘭𝘪𝘵𝘺 𝘰𝘧 𝘓𝘢𝘯𝘨𝘶𝘢𝘨𝘦 𝘔𝘰𝘥𝘦𝘭𝘴 𝘧𝘰𝘳 𝘊𝘰𝘮𝘱𝘶𝘵𝘢𝘵𝘪𝘰𝘯𝘢𝘭 𝘈𝘳𝘨𝘶𝘮𝘦𝘯𝘵𝘢𝘵𝘪𝘰𝘯”, held at Technische Universität Darmstadt on February 17th, 2026.

LMs that "know more" about toxicity are less toxic! Our #TACL 📄 connects behavior and internals: 💠 LMs amplify toxicity beyond humans 💠 Information about toxicity peaks in lower layers 💠 Bypassing these layers increases toxicity More details👇 #NLProc #interpretability (1/🧵)

✨ The schedule for our INTERPLAY workshop at COLM is live! ✨ 🗓️ October 10th, Room 518C 🔹 Invited talks from @sarah-nlp.bsky.social John Hewitt @amuuueller.bsky.social @kmahowald.bsky.social 🔹 Paper presentations and posters 🔹 Closing roundtable discussion. Join us in Montréal! @colmweb.org

Missed a spot? If you have a pre-reviewed paper from ARR or COLM that focuses on the INTERPLAY between LM internals and behavior, there is a shortcut to presenting at our @colmweb.org workshop! ✨ Join us in Montréal! 🇨🇦 CfP: shorturl.at/sBomu OpenReview: shorturl.at/WwWhg #nlproc #interpretability

Delighted that ✨Mor Geva (@megamor2.bsky.social) and ✨Anna Ivanova (@neuranna.bsky.social) will complete our speaker line-up and talk about the INTERPLAY of model internals and behavior. Be there and submit by June 30th 📄 shorturl.at/sBomu See you in 🇨🇦 @colmweb.org #nlproc #interpretability