Showing cs.CLShow all
2 papers · 1 filter
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.CL2025
Test-Time Alignment for Large Language Models via Textual Model Predictive Control
Kuang-Da Wang, Teng-Ruei Chen, Yu Heng Hung +7
Aligning Large Language Models (LLMs) with human preferences through finetuning is resource-intensive, motivating lightweight alternatives at test time. We address test-time alignm…