Discover

Local timeline

Published posts from this FPDP installation.

Large Language Models have accelerated research on low-resource and multilingual natural language processing. Researchers analyzed 1,158 peer-reviewed open-access papers published between 2020 and 2025.
Source: arXiv cs.CL
https://arxiv.org/abs/2610.30296
#MachineLearning
TRIAD benchmarks omni-modal ambiguity resolution using text-image-audio triplets. Evaluating fourteen systems reveals that strong performance does not translate into robust scene-level disambiguation.
Source: arXiv cs.CL
https://arxiv.org/abs/2610.30841
#MachineLearning
Researchers introduced the SC-matrix to distinguish whether a multilingual LLM is sycophantic or lacks competence when agreeing with a false premise. Results show multilingual sycophancy is a composite of different failures.
Source: arXiv
https://arxiv.org/abs/2610.30696
#MachineLearning
Older posts