iiinova — where your digital self keeps evolving

Jing Yang

@jingyng.bsky.social

Post-doc researcher at BIFOLD and the XplaiNLP group from Quality and Usability lab at TU Berlin. Interested in: xAI, fact-checking, synthetic data generation and evaluation

Posts Replies Media

Reposted by Jing Yang

Jing Yang @jingyng.bsky.social · 28/05/2026

📢 Call for Papers We're organizing the 5th edition of MUWS: Workshop Multimodal Human Understanding for the Web and Social Media @ ACM Multimedia 2026 in Rio de Janeiro, Brazil! 🇧🇷 🗓️ Deadline: July 16, 2026 🔗 Full CFP: muws-workshop.github.io/cfp/ #ACMMM #MUWS 🔗 muws-workshop.github.io/cfp/

muws-workshop.github.io

Call for Papers | MUWS 2026

131

Jing Yang @jingyng.bsky.social · 28/05/2026

muws-workshop.github.io

Call for Papers | MUWS 2026

131

Reposted by Jing Yang

Nils Feldhus @nfel.bsky.social · 19/03/2026

Can Persona Prompting function as a lens on social reasoning? In our #EACL2026 work (led by @jingyng.bsky.social), we investigate how it impacts the quality of model outputs and rationales. 🗞️ arXiv: arxiv.org/abs/2601.20757 Come and find us (Jing, Moritz, Elisabeth, myself) in 🇲🇦 Rabat next week!

1102

Reposted by Jing Yang

UKP Lab @ukplab.bsky.social · 25/07/2025

Can LLMs generate explanations for datasets without such annotations? 🧠 We tested model explanations across 19 datasets (NLI, fact-checking, hallucination detection) to see how well they self-rationalize on completely unseen data. #LLMs #Explainability #ACL2025 #TACL

OOD evaluation pipeline of self-rationalization, and OOD datasets categories considered in the paper.

141