Tanise Ceron
@taniseceron.bsky.social
📤 134
📥 158
📝 32
Postdoc
@milanlp.bsky.social
pinned post!
📣 New Preprint! Have you ever wondered what the political content in LLM's training data is? What are the political opinions expressed? What is the proportion of left- vs right-leaning documents in the pre- and post-training data? Do they correlate with the political biases reflected in models?
2 months ago
2
46
14
We go out of the routine every now and then at the lab. :)
add a skeleton here at some point
1 day ago
1
3
0
@agnesedaff.bsky.social
presented our work on "Generalizability of Media Frames: Corpus creation and analysis across countries" at *SEM co-located with EMNLP 2025 in China.
add a skeleton here at some point
5 days ago
1
7
0
Does anyone know any good resource that systematically documents information about the training data of different LLMs (e.g. name of datasets, language proportion, etc whenever available)?
11 days ago
2
1
0
reposted by
Tanise Ceron
MilaNLP Lab
28 days ago
Proud to present our
#EMNLP2025
papers! Catch our team across Main, Findings, Workshops & Demos 👇
12
11
6
📣 New Preprint! Have you ever wondered what the political content in LLM's training data is? What are the political opinions expressed? What is the proportion of left- vs right-leaning documents in the pre- and post-training data? Do they correlate with the political biases reflected in models?
2 months ago
2
46
14
reposted by
Tanise Ceron
arXiv cs.CL Computation and Language
2 months ago
Tanise Ceron, Dmitry Nikolaev, Dominik Stammbach, Debora Nozza: What Is The Political Content in LLMs' Pre- and Post-Training Data?
https://arxiv.org/abs/2509.22367
https://arxiv.org/pdf/2509.22367
https://arxiv.org/html/2509.22367
0
1
3
Today Sourabh Dattawad presented our work "Leveraging Media Frames to Improve Normative Diversity in News Recommendations" at INRA (International Workshop on News Recommendation and Analytics) co-located with RecSys 2025 in Prague.
arxiv.org/pdf/2509.02266
2 months ago
1
2
1
reposted by
Tanise Ceron
Joachim Baumann
3 months ago
🚨 New paper alert 🚨 Using LLMs as data annotators, you can produce any scientific result you want. We call this **LLM Hacking**. Paper:
arxiv.org/pdf/2509.08825
6
268
117
reposted by
Tanise Ceron
MilaNLP Lab
5 months ago
Last week we held our 1st MilaNLP retreat by beautiful Lago Maggiore! ⛰️🌊 We shared research ideas, stories (academic & beyond), and amazing food. It was a great time to connect outside of the usual lab working days, and most importantly, strengthen our bonds as a team.
#ResearchLife
#NLProc
0
22
6
reposted by
Tanise Ceron
Beatrice Savoldi
6 months ago
🔍 Stiamo studiando come l'AI viene usata in Italia e per farlo abbiamo costruito un sondaggio! 👉
bit.ly/sondaggio_ai...
(è anonimo, richiede ~10 minuti, e se partecipi o lo fai girare ci aiuti un sacco🙏) Ci interessa anche raggiungere persone che non si occupano e non sono esperte di AI!
loading . . .
Qualtrics Survey | Qualtrics Experience Management
The most powerful, simple and trusted way to gather experience data. Start your journey to experience management and try a free account today.
https://bit.ly/sondaggio_ai_rita
1
16
18
Reminder for the importance of evaluating political biases robustly. :)
add a skeleton here at some point
7 months ago
0
1
0
reposted by
Tanise Ceron
Dirk Hovy
7 months ago
We (w/
@diyiyang.bsky.social
,
@zhuhao.me
, & Bodhisattwa Prasad Majumder) are excited to present our
#NAACL25
tutorial on Social Intelligence in the Age of LLMs! It will highlight long-standing and emerging challenges of AI interacting w humans, society & the world. ⏰ May 3, 2:00pm-5:30pm Room Pecos
0
14
6
reposted by
Tanise Ceron
Verena Kunz
7 months ago
Join us in an hour at 17:00 (CEST) for
@taniseceron.bsky.social
's talk on "Evaluating Political Bias: Insights into Robustness and Multilinguality“. Access to Zoom at
join.slack.com/t/tadapolisc...
or send me a ✉️
add a skeleton here at some point
0
1
1
reposted by
Tanise Ceron
Christopher Klamm 🌱
7 months ago
🥁 It's the second half of our 🌱 speaker series (
tada.cool
) this term, and we couldn't be more excited! Next week (Wednesday, April 30 at 5pm CET), we have the pleasure of welcoming
@taniseceron.bsky.social
to share insights on "Facilitating Information Access Through Language Models". More details ⬇️
add a skeleton here at some point
0
7
5
reposted by
Tanise Ceron
Dirk Hovy
9 months ago
Wanna keep up with our
@milanlp.bsky.social
lab? Here is a starter pack of current and former members:
bsky.app/starter-pack...
add a skeleton here at some point
0
13
7
Happy to be presenting at
#TaDa
and looking forward to watching the great talks coming up. :)
add a skeleton here at some point
9 months ago
0
3
2
🤯 Perhaps it's time to start challenging the culture in our area of "submitting to get some feedback". Isn't it more productive to submit only when we feel the paper is really ready to be submitted?
add a skeleton here at some point
9 months ago
3
12
1
you reached the end!!
feeds!
log in
