Niklas Stoehr
@niklasstoehr.bsky.social
📤 1095
📥 218
📝 7
Gemini Post-Training ⚫️ Research Scientist at Google DeepMind ⚫️ PhD from ETH Zurich
reposted by
Niklas Stoehr
Alexander Hoyle
11 days ago
Very delighted to announce the next step in my career! After my postdoc at ETH, I will begin a joint appointment at TU Wien and the Complexity Science Hub Vienna as an Assistant Professor in NLP. I'm so grateful to all who helped me along the way And yes, I’m hiring! Details on PhD positions below
10
96
13
reposted by
Niklas Stoehr
2 months ago
✨The NLP+CSS workshop is returning to ACL 2026!✨ Our commitment deadline for pre-reviewed ARR submissions has been extended to April 5! Website/CfP:
sites.google.com/site/nlpandc...
#NLProc
#CompSocialSci
#ComputationalSocialScience
#ACL2026NLP
@aclmeeting.bsky.social
loading . . .
NLP+CSS Workshops - Call for Papers - 2026
Language is deeply intertwined with nearly all human social processes. We do not expect teenagers to speak like senior citizens, and we recognize the mutual dependency between language and the ways pe...
https://sites.google.com/site/nlpandcss/2026-acl/call-for-papers-2026
0
5
3
reposted by
Niklas Stoehr
Luca Beurer-Kellner
4 months ago
(1/n) We analyzed 3,984 agent skills from major marketplaces and found 76 malicious payloads, including credential theft, backdoor installation, and data exfiltration. Also, 13.4% contain at least on critical-level vuln. Full report below, highlights in thread 👇
github.com/invariantlab...
1
3
1
reposted by
Niklas Stoehr
Giuliano Formisano
6 months ago
📣📣 New paper with
#JoergFriedrichs
,
@florianschaffner.bsky.social
,
@niklasstoehr.bsky.social
, “Populism and governmentalism as thin-centered ideologies: Emotions and frames on social media” is out at
@ejprjournal.bsky.social
Read more:
doi.org/10.1017/S147...
1
22
5
🔓What brought me into Machine Learning research is its universal applicability—pattern recognition underlies all empirical sciences and even lets you publish in top polscience journals such as EJPR:
shorturl.at/8e1rF
@giulianoformisano.bsky.social
@florianschaffner.bsky.social
and Joerg Friedrichs.
6 months ago
0
2
1
⚖️ Measuring Scalar Constructs in Social Science with LLMs with rising (and established) stars in Computational Social Science
@haukelicht.bsky.social
@rupak-s.bsky.social
@patrickwu.bsky.social
@pranavgoel.bsky.social
@elliottash.bsky.social
@alexanderhoyle.bsky.social
arxiv.org/abs/2509.03116
7 months ago
0
15
4
reposted by
Niklas Stoehr
Alexander Hoyle
7 months ago
Paper:
arxiv.org/abs/2509.03116
Code:
github.com/haukelicht/s..
. With:
@haukelicht.bsky.social
*
@rupak-s.bsky.social
*
@patrickwu.bsky.social
@pranavgoel.bsky.social
@niklasstoehr.bsky.social
@elliottash.bsky.social
loading . . .
https://github.com/haukelicht/s..
0
6
1
reposted by
Niklas Stoehr
Alexander Hoyle
7 months ago
[corrected link] LLMs are often used for text annotation in social science. In some cases, this involves placing text items on a scale: eg, 1 for liberal and 9 for conservative There are a few ways to handle this task. Which work best? Our new EMNLP paper has some answers🧵
arxiv.org/abs/2509.03116
1
25
5
reposted by
Niklas Stoehr
Alexander Hoyle
11 months ago
Evaluating topic models (and document clustering methods) is hard. In fact, since our paper critiquing standard evaluation practices four years ago, there hasn't been a good replacement metric That ends today (we hope)! Our new ACL paper introduces an LLM-based evaluation protocol 🧵
3
53
12
🎓 I recently defended my PhD and moved from one dream team at ETH Zurich to another at DeepMind—a huge thank you to the many people who have supported me along the way!
12 months ago
0
32
0
reposted by
Niklas Stoehr
Shauli Ravfogel
over 1 year ago
Our paper "A Practical Method for Generating String Counterfactuals" has been accepted to the findings of NAACL 2025! a joint work with
@matan-avitan.bsky.social
,
@yoavgo.bsky.social
and Ryan Cotterell. We propose "Intervention Lens", a technique to explain intervention in natural language. (1/6)
1
38
6
reposted by
Niklas Stoehr
Paul Röttger
over 1 year ago
Are LLMs biased when they write about political issues? We just released IssueBench – the largest, most realistic benchmark of its kind – to answer this question more robustly than ever before. Long 🧵with spicy results 👇
4
82
31
reposted by
Niklas Stoehr
Julian Minder
over 1 year ago
Can we understand and control how language models balance context and prior knowledge? Our latest paper shows it’s all about a 1D knob! 🎛️
arxiv.org/abs/2411.07404
Co-led with
@kevdududu.bsky.social
-
@niklasstoehr.bsky.social
, Giovanni Monea,
@wendlerc.bsky.social
, Robert West & Ryan Cotterell.
1
13
3
reposted by
Niklas Stoehr
Lucy Li
over 1 year ago
mech interp:
bsky.app/starter-pack...
women in nlp:
bsky.app/starter-pack...
nlp #1:
bsky.app/starter-pack...
nlp #2:
bsky.app/starter-pack...
ml/data/tech:
bsky.app/starter-pack...
robotics & ai:
bsky.app/starter-pack...
add a skeleton here at some point
7
73
23
reposted by
Niklas Stoehr
Sweta Karlekar
over 1 year ago
If you’re interested in mechanistic interpretability, I just found this starter pack and wanted to boost it (thanks for creating it
@butanium.bsky.social
!). Excited to have a mech interp community on bluesky 🎉
go.bsky.app/LisK3CP
add a skeleton here at some point
3
36
10
reposted by
Niklas Stoehr
Giuliano Formisano
over 1 year ago
Just launched a Political Comm/NLP/Text-as-Data Starter Pack. 🦋🤗 Join us and/or drop a message to be added!
go.bsky.app/39MWTjg
#starterpack
#polsci
add a skeleton here at some point
3
30
10
reposted by
Niklas Stoehr
Vilém Zouhar
over 1 year ago
Trying to bring ML/NLP/etal people from ETH Zürich together. Ping me to add you. 🙂
bsky.app/starter-pack...
add a skeleton here at some point
1
26
6
you reached the end!!
feeds!
log in