Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
UniSD: Towards a Unified Self-Distillation Framework for Large Language Models
Yiqiao Jin, Yiyang Wang, Lucheng Fu +8
Self-distillation (SD) offers a promising path for adapting large language models (LLMs) without relying on stronger external teachers. However, SD in autoregressive LLMs remains c…
cs.CL2026
TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization
Lucheng Fu, Ye Yu, Yiyang Wang +4
Large language models (LLMs) are highly sensitive to the prompts used to specify task objectives and behavioral constraints. Many recent prompt optimization methods iteratively rew…
cs.CL2026
MASCOT: Multi-Agent Socio-Collaborative Companion Systems
Yiyang Wang, Yiqiao Jin, Alex Cabral +1
Multi-agent systems (MAS) are emerging as promising socio-collaborative companions for emotional and cognitive support. However, existing systems frequently suffer from persona col…