@taniseceron.bsky.social is presenting her work about political content in pre-training and post-training data at the AI & Society conference. #AIandSociety #NLProc

Come join our group! Still one day left for applying. 😊

Dirk Hovy@dirkhovy.bsky.social · 7mo ago

New year, new job? If that is your current mantra, check the open postdoc positions with Debora Nozza and me at our lab. Deadline is January 31st. milanlproc.github.io/open_positio...

Some findings that I find particularly impactful for the area of political biases in LLMs: 1) Aligning LLMs with DPO on left-leaning opinions does not have a significant impact on the stance of the models given that vanilla LLMs already reflect a more left-leaning alignment.

Franzi Weeber@franziweeber.bsky.social · 6mo ago

Paper accepted to #EACL2026 main conference 🎉 @taniseceron.bsky.social, Sebastian Padó and I test multilingual LLMs before and after English-only fine-tuning and find strong cross-lingual political opinion transfer across five Western languages. www.arxiv.org/abs/2508.05553

🚀 We’re opening 2 fully funded postdoc positions in #NLP! Join the MilaNLP team and contribute to our upcoming research projects. 🔗 More details: milanlproc.github.io/open_positio... ⏰ Deadline: Jan 31, 2026

I will be @euripsconf.bsky.social this week to present our paper as non-archival at the PAIG workshop (Beyong Regulation: Private Governance & Oversight Mechanisms for AI). Very much looking forward to the discussions! If you are at #EurIPS and want to chat about LLM's training data. Reach out!

Tanise Ceron@taniseceron.bsky.social · 10mo ago

📣 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?

We go out of the routine every now and then at the lab. :)

MilaNLP Lab@milanlp.bsky.social · 8mo ago

Another exhausting day in the lab… conducting very rigorous panettone analysis. Pandoro was evaluated too, because we believe in fair experimental design.

@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.

MilaNLP Lab@milanlp.bsky.social · 8mo ago

What an inspiring week at #EMNLP2025 in Suzhou🇨🇳! Huge thanks to the organizers and everyone who stopped by our poster/talk!

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)?

Proud to present our #EMNLP2025 papers! Catch our team across Main, Findings, Workshops & Demos 👇

📣 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?

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

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

🚨 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

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

🔍 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!

Reminder for the importance of evaluating political biases robustly. :)

MilaNLP Lab@milanlp.bsky.social · last yr.

#MemoryMonday #NLProc Beyond Prompt Brittleness: Evaluating the Reliability and Consistency of Political Worldviews in LLMs" (@taniseceron.bsky.social et al.,) evaluate the consistency of political worldviews in LLMs, unveiling fine-grained stances in policy issues.

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

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 ✉️

Verena Kunz@verenakunz.bsky.social · last yr.

The #TaDa Speaker Series is back for the spring 🎉 We're looking forward to an exciting line-up of talks by @prashantgarg.bsky.social, @miriamschirmer.bsky.social, @chdausgaard.bsky.social, @taniseceron.bsky.social, @lukashetzer.bsky.social, and Catarina Pereira! More infos at tada.cool & on Slack ⬇️

🥁 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 ⬇️

Verena Kunz@verenakunz.bsky.social · last yr.

The #TaDa Speaker Series is back for the spring 🎉 We're looking forward to an exciting line-up of talks by @prashantgarg.bsky.social, @miriamschirmer.bsky.social, @chdausgaard.bsky.social, @taniseceron.bsky.social, @lukashetzer.bsky.social, and Catarina Pereira! More infos at tada.cool & on Slack ⬇️

Wanna keep up with our @milanlp.bsky.social lab? Here is a starter pack of current and former members: bsky.app/starter-pack...

Happy to be presenting at #TaDa and looking forward to watching the great talks coming up. :)

Verena Kunz@verenakunz.bsky.social · last yr.

The #TaDa Speaker Series is back for the spring 🎉 We're looking forward to an exciting line-up of talks by @prashantgarg.bsky.social, @miriamschirmer.bsky.social, @chdausgaard.bsky.social, @taniseceron.bsky.social, @lukashetzer.bsky.social, and Catarina Pereira! More infos at tada.cool & on Slack ⬇️

🤯 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?

Juraj Vladika@jvladika.bsky.social · last yr.

More than 8500 submissions to ACL 2025 (ARR February 2025 cycle)! That is an increase of 3000 submissions compared to ACL 2024. It will be a fun reviewing period. 😅💯 @aclmeeting.bsky.social #ACL2025 #ACL2025nlp #NLP