3 papers
cs.CL2026
SLAP: Stratified Loss-based Pruning for On-Policy Data-Efficient Instruction Tuning
Run Zou, Jianhang Ding, Yifan Ding +3
Instruction tuning has optimized the specialized capabilities of large language models (LLMs), but it often requires extensive datasets and prolonged training times. The challenge…
cs.CL2025
Efficient Tuning of Large Language Models for Knowledge-Grounded Dialogue Generation
Bo Zhang, Hui Ma, Dailin Li +4
Large language models (LLMs) demonstrate remarkable text comprehension and generation capabilities but often lack the ability to utilize up-to-date or domain-specific knowledge not…
cs.CL2025
Distilling Implicit Multimodal Knowledge into Large Language Models for Zero-Resource Dialogue Generation
Bo Zhang, Hui Ma, Jian Ding +3
Integrating multimodal knowledge into large language models (LLMs) represents a significant advancement in dialogue generation capabilities. However, the effective incorporation of…