Showing 2026Show all
3 papers · 1 filter
cs.LG2026
PIVOT: Perplexity-Informed KD-to-RL Transition Scheduling for Vertical-Domain Few-Shot Distillation
Heng Li, Yong Zhang, Ning Cheng +5
Vertical-domain few-shot classification remains challenging for small language models, as limited supervision makes it difficult to acquire domain-specific decision knowledge. On-P…
cs.CL2026
Astra: Activation-Space Tail-Eigenvector Low-Rank Adaptation of Large Language Models
Kainan Liu, Yong Zhang, Ning Cheng +4
Parameter-Efficient Fine-Tuning (PEFT) methods, especially LoRA, are widely used for adapting pre-trained models to downstream tasks due to their computational and storage efficien…
cs.CL2026
Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry
Zhuochun Li, Yong Zhang, Ming Li +8
Large language models (LLMs) are widely used as reference-free evaluators via prompting, but this "LLM-as-a-Judge" paradigm is costly, opaque, and sensitive to prompt design. In th…