2 papers
cs.CL2026
Summarize Before You Speak with ARACH: A Training-Free Inference-Time Plug-In for Enhancing LLMs via Global Attention Reallocation
Jingtao Wang, Yucong Wang, Jun Ding +2
Large language models (LLMs) achieve remarkable performance, yet further gains often require costly training. This has motivated growing interest in post-training techniques-especi…
cs.LG2024
Adapting LLMs for Efficient Context Processing through Soft Prompt Compression
Cangqing Wang, Yutian Yang, Ruisi Li +5
The rapid advancement of Large Language Models (LLMs) has inaugurated a transformative epoch in natural language processing, fostering unprecedented proficiency in text generation,…