iiinova — where your digital self keeps evolving

Reposted by Franzi Weeber

Gabriella Lapesa @gabriellalapesa.bsky.social · 14/07/2026

We are super excited to have received 45 direct submissions! And if you have an ARR-reviewed paper that was rejected elsewhere, you still have time until ***tomorrow*** to submit it to CPSS @ #KONVENS2026 ! So we look forward to more submissions!

011

Franzi Weeber @franziweeber.bsky.social · 16/06/2026

🗓️ The workshop features a keynote talk, a panel discussion on human perspectives in LLMs, poster presentations of accepted archival and non-archival work, and a PhD forum for doctoral students at any stage of their PhD to present their PhD topic and receive feedback. (3/3)

000

Franzi Weeber @franziweeber.bsky.social · 16/06/2026

💡 This year's edition of CPSS explores the special focus topic of human perspectives in LLMs. We also welcome research on computational social science, human-centered perspectives in language technologies, the societal implications of LLMs and AI, and many more topics. (2/3)

100

Franzi Weeber @franziweeber.bsky.social · 16/06/2026

🚨 Final Call for Papers: CPSS @ #KONVENS2026 🚨 Join us in Hamburg on September 14 (14.00-17.00) and 15 (9.00-12.00) to share your research at the intersection of NLP and social/political science. ⏳ Deadline: July 3, 2026 (23:59 CET) 🌐 sites.google.com/view/cpss202... #CompSocSci #NLP #CFP (1/3)

sites.google.com

CPSS 2026 @ KONVENS

This is the 6th edition of the workshop on Computational Linguistics for the Political and Social Sciences (CPSS), co-located with the KONVENS conference. Our main goal is to bring together researcher...

136

Franzi Weeber @franziweeber.bsky.social · 07/04/2026

Easter brought great news: Our paper was accepted to the #ACL2026 main conference!

020

Reposted by Franzi Weeber

Vera Neplenbroek @veraneplenbroek.bsky.social · 07/04/2026

Excited to share that our paper "One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization" (joint work with @franziweeber.bsky.social, Jan Batzner and Sebastian Padó) got accepted to the main conference of #ACL 🎉

081

Franzi Weeber @franziweeber.bsky.social · 06/04/2026

Two weeks ago, I presented our paper 'Do Political Opinions Transfer Between Western Languages?' at #EACL2026 main conference in Rabat, Morocco. It was amazing to discuss our and other people's research there! Check out the paper here: aclanthology.org/2026.eacl-lo...

030

Franzi Weeber @franziweeber.bsky.social · 30/01/2026

Alignment with demographic subgroups can look good for single survey questions, yet miss the correlation structure of cultural values. Tristan Williams, Sebastian Padó, Alan Akbik and I propose a 2-level eval framework and apply it to demographically aligned LLMs. arxiv.org/abs/2601.15755

040

Franzi Weeber @franziweeber.bsky.social · 29/01/2026

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

092

Franzi Weeber @franziweeber.bsky.social · 28/01/2026

While the responses for different cues are highly correlated, we find stronger biases for more explicit but less externally valid cues. We advise future work to focus on externally valid cues such as human written conversation histories or to base their findings on a mixture of cues (2/2)

010

Franzi Weeber @franziweeber.bsky.social · 28/01/2026

Even with identical sociodemographic info, how LLMs are given it changes downstream bias results. Our new preprint (w/ @veraneplenbroek.bsky.social, Jan Batzner & Sebastian Padó) tests cues with varying external validity across 10 personas, 4 tasks & 7 LLMs: arxiv.org/abs/2601.18572

Different sociodemographic cues for gender (male, female, and non-binary personas) result in different LLM answers to a medical advice request.

1100