Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference
Lang Zhou, Shuxuan Li, Zhuohao Li +3
Long-context inference remains challenging for large language models due to attention dilution and out-of-distribution degradation. Context selection mitigates this limitation by a…
cs.CL2025
Paper Summary Attack: Jailbreaking LLMs through LLM Safety Papers
Liang Lin, Zhihao Xu, Xuehai Tang +5
The safety of large language models (LLMs) has garnered significant research attention. In this paper, we argue that previous empirical studies demonstrate LLMs exhibit a propensit…