2 papers
cs.CL2026
Exposing Long-Tail Safety Failures in Large Language Models through Efficient Diverse Response Sampling
Suvadeep Hajra, Palash Nandi, Tanmoy Chakraborty
Safety tuning through supervised fine-tuning and reinforcement learning from human feedback has substantially improved the robustness of large language models. However, it typicall…
cs.LG2025
Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training
Suvadeep Hajra
Autoregressive transformer language models frequently exhibit training instability when trained on long sequences, particularly under low-precision arithmetic. Although this instab…