2 papers
cs.CL2026
Lost in Translation? A Comparative Study on the Cross-Lingual Transfer of Composite Harms
Vaibhav Shukla, Hardik Sharma, Adith N Reganti +3
Most safety evaluations of large language models (LLMs) remain anchored in English. Translation is often used as a shortcut to probe multilingual behavior, but it rarely captures t…
cs.LG2026
Pay for Hints, Not Answers: LLM Shepherding for Cost-Efficient Inference
Ziming Dong, Hardik Sharma, Evan O'Toole +2
Large Language Models (LLMs) deliver state-of-the-art performance on complex reasoning tasks, but their inference costs limit deployment at scale. Small Language Models (SLMs) offe…