Search papers, labs, and topics across Lattice.
Sorbonne Universit茅
2
0
5
LLMs show a striking bias, being more perplexed by far-right texts, which raises concerns about their political fairness in real-world applications.
Despite advancements in OCR, current models fail to generalize beyond a small set of scripts, often hallucinating characters or producing noise when faced with unfamiliar writing systems.
