Crowdsourcing datasets is very common, but how much of those results come from LLMs these days? How can we prevent it? Much of it is unclear. This is why weโre conducing a survey (~10 min) to gather community experiences, challenges, and solutions.
Share your thoughts ๐https://tinyurl.com/39ab55wf
๐ Meet our #SoftwareCampus participant @nlp-amelie.bsky.social, PhD student at Universitรคt #Stuttgart. She is collaborating with #Merck on building #AI models to detect & analyze treatment expectations from patients on #SocialMedia posts.
๐ Click here:
softwarecampus.de/en/projekt/p...
#NLP
I've turned the page to a new academic chapter & started a postdoc position @itu.dk in Copenhagen ๐ I'll be working with @annarogers.bsky.social in the PlagAIrism project, where we develop methods to identify & cite sources in LLM training data that contributed to a generated text.
My friends are organizing a new workshop bringing together NLP and CSS research with psychology: First Workshop on Integrating NLP and Psychology to Study Social Interactions (NLPSI) at ICWSM 2025 nlpsi-workshop.github.io Consider submitting a paper (long/short) or an extended abstract :)
Can Community Notes Replace Professional Fact-Checkers? Work done by Nadav Borenstein, Greta Warren, Desmond Elliott, and Isabelle Augenstein.
๐จ Preprint alert ๐จ
๐๐๐ง ๐๐จ๐ฆ๐ฆ๐ฎ๐ง๐ข๐ญ๐ฒ ๐๐จ๐ญ๐๐ฌ ๐๐๐ฉ๐ฅ๐๐๐ ๐๐ซ๐จ๐๐๐ฌ๐ฌ๐ข๐จ๐ง๐๐ฅ ๐
๐๐๐ญ-๐๐ก๐๐๐ค๐๐ซ๐ฌ?
(arxiv.org/abs/2502.14132)
Fact-checking agencies have come under intense scrutiny in recent months regarding their role in combating misinformation on social media.
Check out the paper: "MOPO: Multi-Objective Prompt Optimization for Affective Text Generation" at COLING 2025. ๐ฅณ
aclanthology.org/2025.coling-...
๐Session 2, Posters - Jan 24 at 13:30-15:00 at Atrium.
Look for Yarik Menchaca for an interesting discussion!
#COLING2025 #NLProc #NLP #COLING
We have a new preprint online where we propose a self-adaptive, iterative framework for claim extraction. The goal is to adapt the way a claim is phrased using a preference signal coming from a fact checking model. Check it out here: arxiv.org/abs/2412.11653
Could you add me (@nlp-amelie.bsky.social) to the list please? Thanks! :)
