4 papers
'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection
Fawzia Zehra, Kara-Isitt, Sonal Khosla +1
Urdu, the world's tenth most spoken language with 246 million speakers, remains almost entirely absent from mainstream LLM safety evaluation and nine years of WOAH proceedings. To…
Hatebench in the era of safer LLMs
Ole Becker, Tobias Jongen, Philip Kolbe +2
As Large Language Models (LLMs) lower the barrier for au- tomated content generation, the potential for producing hate speech poses a significant challenge for digital safety. This…
LLM Compression: How Far Can We Go in Balancing Size and Performance?
Sahil Sk, Debasish Dhal, Sonal Khosla +6
Quantization is an essential and popular technique for improving the accessibility of large language models (LLMs) by reducing memory usage and computational costs while maintainin…
Building a Llama2-finetuned LLM for Odia Language Utilizing Domain Knowledge Instruction Set
Guneet Singh Kohli, Shantipriya Parida, Sambit Sekhar +6
Building LLMs for languages other than English is in great demand due to the unavailability and performance of multilingual LLMs, such as understanding the local context. The probl…