Franzi Weeber
@franziweeber.bsky.social
PhD Student @ IMS Stuttgart
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
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
January 30, 2026 at 1:50 PM
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
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
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
@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
January 29, 2026 at 9:09 AM
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
@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
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)
January 28, 2026 at 4:22 PM
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)
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
January 28, 2026 at 4:22 PM
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