3 papers
cs.CL2026
Memory for Large Language Models
Sining Zhoubian, Dan Zhang, Evgeny Kharlamov +1
Memory has evolved into a foundational architectural dimension in large language models (LLMs), shifting from an implicit byproduct of computation to a spectrum of explicit, contro…
cs.CL2026
Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding
Xuanming Zhang, Sining Zhoubian, Yuxuan Chen +8
Autoregressive generation in large language models (LLMs) conventionally decodes from the final layer, assuming that deeper representations yield more reliable next-token predictio…
cs.CL2025
DataSciBench: An LLM Agent Benchmark for Data Science
Dan Zhang, Sining Zhoubian, Min Cai +7
This paper presents DataSciBench, a comprehensive benchmark for evaluating Large Language Model (LLM) capabilities in data science. Recent related benchmarks have primarily focused…