2 papers
cs.LG2025
When Refusals Fail: Unstable Safety Mechanisms in Long-Context LLM Agents
Tsimur Hadeliya, Mohammad Ali Jauhar, Nidhi Sakpal +1
Solving complex or long-horizon problems often requires large language models (LLMs) to use external tools and operate over a significantly longer context window. New LLMs enable l…
cs.CL2024
Evaluation of Few-Shot Learning for Classification Tasks in the Polish Language
Tsimur Hadeliya, Dariusz Kajtoch
We introduce a few-shot benchmark consisting of 7 different classification tasks native to the Polish language. We conducted an empirical comparison with 0 and 16 shots between fin…