Sen Song

UniMem: Towards a Unified View of Long-Context Large Language Models

2024 · arXiv (Cornell University)

Long-context processing is a critical ability that constrains the applicability of large language models (LLMs). Although there exist various methods devoted to enhancing the long-context processing ability of LLMs, they are developed in an isolated …

Unsupervised Paraphrasing by Simulated Annealing

2020

We propose UPSA, a novel approach that accomplishes Unsupervised Paraphrasing by Simulated Annealing. We model paraphrase generation as an optimization problem and propose a sophisticated objective function, involving semantic similarity, expression diversity, and language fluency …