Lightnews — Scholar-powered news

Reposted by Marius Mosbach

Gaurav Kamath @grvkamath.bsky.social · Jul 29

Our new paper in #PNAS (bit.ly/4fcWfma) presents a surprising finding—when words change meaning, older speakers rapidly adopt the new usage; inter-generational differences are often minor.

w/ Michelle Yang, ‪@sivareddyg.bsky.social‬ , @msonderegger.bsky.social‬ and @dallascard.bsky.social‬👇(1/12)

3 17 33

Reposted by Marius Mosbach

Ingmar Weber @ingmarweber.de · Jul 18

🚨Job Alert
W2 (TT W3) Professorship in Computer Science "AI for People & Society"
@saarland-informatics-campus.de/@uni-saarland.de is looking to appoint an outstanding individual in the field of AI for people and society who has made significant contributions in one or more of the following areas:

1 18 14

Reposted by Marius Mosbach

Abhilasha Ravichander @lasha.bsky.social · Jul 22

📣 Life update: Thrilled to announce that I’ll be starting as faculty at the Max Planck Institute for Software Systems this Fall!

I’ll be recruiting PhD students in the upcoming cycle, as well as research interns throughout the year: lasharavichander.github.io/contact.html

13 12 89

Reposted by Marius Mosbach

Sebastian Bordt @sbordt.bsky.social · Jul 14

I'm at #ICML in Vancouver this week, hit me up if you want to chat about pre-training experiments or explainable machine learning.

You can find me at these posters:

Tuesday: How Much Can We Forget about Data Contamination? icml.cc/virtual/2025...

1 1 1

Marius Mosbach @mariusmosbach.bsky.social · Jul 14

Congrats!

1

Reposted by Marius Mosbach

Tiago Pimentel @tpimentel.bsky.social · Jul 14

Mechanistic interpretability often relies on *interventions* to study how DNNs work. Are these interventions enough to guarantee the features we find are not spurious? No!⚠️ In our new paper, we show many mech int methods implicitly rely on the linear representation hypothesis🧵

Paper title "The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?" with the paper's graphical abstract showing how more powerful alignment maps between a DNN and an algorithm allow more complex features to be found and more "accurate" abstractions.

1 12 62

Reposted by Marius Mosbach

Sebastian Bordt @sbordt.bsky.social · Jul 8

Have you ever wondered whether a few times of data contamination really lead to benchmark overfitting?🤔 Then our latest #ICML paper about the effect of data contamination on LLM evals might be for you!🚀

Paper: arxiv.org/abs/2410.03249
👇🧵

1 1 12

Reposted by Marius Mosbach

Valentina Pyatkin @valentinapy.bsky.social · Jul 3

💡Beyond math/code, instruction following with verifiable constraints is suitable to be learned with RLVR.
But the set of constraints and verifier functions is limited and most models overfit on IFEval.
We introduce IFBench to measure model generalization to unseen constraints.

1 5 29

Reposted by Marius Mosbach

Cesare @cesare-spinoso.bsky.social · Jun 26

A blizzard is raging through Montreal when your friend says “Looks like Florida out there!” Humans easily interpret irony, while LLMs struggle with it. We propose a 𝘳𝘩𝘦𝘵𝘰𝘳𝘪𝘤𝘢𝘭-𝘴𝘵𝘳𝘢𝘵𝘦𝘨𝘺-𝘢𝘸𝘢𝘳𝘦 probabilistic framework as a solution.
Paper: arxiv.org/abs/2506.09301 to appear @ #ACL2025 (Main)

1 7 15

Reposted by Marius Mosbach

Benno Krojer @bennokrojer.bsky.social · Jun 25

Started a new podcast with @tomvergara.bsky.social !

Behind the Research of AI:
We look behind the scenes, beyond the polished papers 🧐🧪

If this sounds fun, check out our first "official" episode with the awesome Gauthier Gidel
from @mila-quebec.bsky.social :

open.spotify.com/episode/7oTc...

02 | Gauthier Gidel: Bridging Theory and Deep Learning, Vibes at Mila, and the Effects of AI on Art

Behind the Research of AI · Episode

open.spotify.com

1 6 17

Marius Mosbach @mariusmosbach.bsky.social · Jun 21

Cool work! You might be interested in our recent work on another problem of existing unlearning methods: arxiv.org/abs/2504.05058

Not All Data Are Unlearned Equally

Machine unlearning is concerned with the task of removing knowledge learned from particular data points from a trained model. In the context of large language models (LLMs), unlearning has recently re...

arxiv.org

2

Reposted by Marius Mosbach

Valentina Pyatkin @valentinapy.bsky.social · Jun 17

Interested in shaping the progress of responsible AI and meeting leading researchers in the field? SoLaR@COLM 2025 is looking for paper submissions and reviewers!

🤖 ML track: algorithms, math, computation
📚 Socio-technical track: policy, ethics, human participant research

1 1 8

Reposted by Marius Mosbach

Xing Han Lu @xhluca.bsky.social · Jun 14

"Build the web for agents, not agents for the web"

This position paper argues that rather than forcing web agents to adapt to UIs designed for humans, we should develop a new interface optimized for web agents, which we call Agentic Web Interface (AWI).

arxiv.org/abs/2506.10953

4 6

Reposted by Marius Mosbach

Benno Krojer @bennokrojer.bsky.social · Jun 13

Excited to share the results of my recent internship!

We ask 🤔
What subtle shortcuts are VideoLLMs taking on spatio-temporal questions?

And how can we instead curate shortcut-robust examples at a large-scale?

We release: MVPBench

Details 👇🔬

1 5 16

Marius Mosbach @mariusmosbach.bsky.social · Jun 13

Congrats Sarah!! They are lucky to have you 💪

1

Reposted by Marius Mosbach

Badr M. Abdullah, PhD @badralabsi.bsky.social · Jun 10

New paper in Interspeech 2025 🚨
@interspeech.bsky.social

A Robust Model for Arabic Dialect Identification using Voice Conversion

Paper 📝 arxiv.org/pdf/2505.24713
Demo 🎙️https://shorturl.at/rrMm6

#Arabic #SpeechTech #NLProc #AI #Speech #ArabicDialects #Interspeech2025 #ArabicNLP

1 2 1

Reposted by Marius Mosbach

Ziling Cheng @ziling-cheng.bsky.social · Jun 6

Do LLMs hallucinate randomly? Not quite.

Our #ACL2025 (Main) paper shows that hallucinations under irrelevant contexts follow a systematic failure mode — revealing how LLMs generalize using abstract classes + context cues, albeit unreliably.

📎 Paper: arxiv.org/abs/2505.22630 1/n

1 18 46

Marius Mosbach @mariusmosbach.bsky.social · May 30

Congrats Elinor!

1

Reposted by Marius Mosbach

Michael Hahn @m-hahn.bsky.social · May 5

Chain-of-Thought (CoT) reasoning lets LLMs solve complex tasks, but long CoTs are expensive. How short can they be while still working? Our new ICML paper tackles this foundational question.

2 2 11

Reposted by Marius Mosbach

Vagrant Gautam @dippedrusk.com · May 3

Come to my keynote tomorrow at the first official @queerinai.com workshop at #NAACL2025 to hear about how trans languaging is complex and cool, and how this makes it extra difficult to process computationally. I will have SO many juicy examples!

Title slide: Processing Trans Languaging - Vagrant Gautam (they/xe), Saarland University, with a very brightly patterned background featuring colourful people and math symbols.

3 14 44

Reposted by Marius Mosbach

hadasorgad.bsky.social @hadasorgad.bsky.social · May 3

Deadline extended! ⏳

The Actionable Interpretability Workshop at #ICML2025 has moved its submission deadline to May 19th. More time to submit your work 🔍🧠✨ Don’t miss out!

3 4

Marius Mosbach @mariusmosbach.bsky.social · May 2

Very interesting work! We also compared ICL and finetuning a while ago. You might find it relevant: aclanthology.org/2023.finding...

Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation

Marius Mosbach, Tiago Pimentel, Shauli Ravfogel, Dietrich Klakow, Yanai Elazar. Findings of the Association for Computational Linguistics: ACL 2023. 2023.

aclanthology.org

1 8

Marius Mosbach @mariusmosbach.bsky.social · May 2

Check out Gaurav's video on their #NAACL paper and find @adadtur.bsky.social at the conference 👇

Mila - Institut québécois d'IA @mila-quebec.bsky.social · May 1

Congratulations to Mila members @adadtur.bsky.social , Gaurav Kamath and @sivareddyg.bsky.social for their SAC award at NAACL! Check out Ada's talk in Session I: Oral/Poster 6. Paper: arxiv.org/abs/2502.05670

1 10

Reposted by Marius Mosbach

Valentina Pyatkin @valentinapy.bsky.social · Apr 27

I'll be at #NAACL2025:

🖇️To present my paper "Superlatives in Context", showing how the interpretation of superlatives is very context dependent and often implicit, and how LLMs handle such semantic underspecification

🖇️And we will present RewardBench on Friday

Reach out if you want to chat!

1 5 28

Marius Mosbach @mariusmosbach.bsky.social · Apr 27

👋🇨🇦🇩🇪

1