4 papers
MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context Inference
Yu Li, Binxu Li, Tian Lan
Autoregressive decoding in Transformer-based language models relies on the KV cache, whose memory footprint grows linearly with sequence length and becomes the primary bottleneck f…
CNSocialDepress: A Chinese Social Media Dataset for Depression Risk Detection and Structured Analysis
Jinyuan Xu, Tian Lan, Xintao Yu +6
Depression is a pressing global public health issue, yet publicly available Chinese-language resources for depression risk detection remain scarce and largely focus on binary class…
Exploring the Capability Boundaries of LLMs in Mastering of Chinese Chouxiang Language
Dianqing Lin, Tian Lan, Jiali Zhu +7
While large language models (LLMs) have achieved remarkable success in general language tasks, their performance on Chouxiang Language, a representative subcultural language in the…
Attention Consistency for LLMs Explanation
Tian Lan, Jinyuan Xu, Xue He +2
Understanding the decision-making processes of large language models (LLMs) is essential for their trustworthy development and deployment. However, current interpretability methods…