Search papers, labs, and topics across Lattice.
Indian Institute of Technology Gandhinagar
2
0
4
Multilingual LLMs face unique toxicity challenges that could undermine safety efforts if not addressed, risking the suppression of legitimate cultural expressions.
Multilingual LLM performance disparities aren't random noise: language features and model biases systematically explain up to 92% of the variance, revealing concrete targets for improvement.
