Výsledky vyhledávání

Report

Perception Compressor:A training-free prompt compression method in long context scenarios

Autor: Tang, Jiwei, Xu, Jin, Lu, Tingwei, Zhang, Zhicheng, Zhao, Yiming, Hai, Lin, Zheng, Hai-Tao

Large Language Models (LLMs) demonstrate exceptional capabilities in various scenarios. However, they suffer from much redundant information and are sensitive to the position of key information (relevant to the input question) in long context scenari

Externí odkaz: http://arxiv.org/abs/2409.19272

Zobrazit plný text záznamu

Report

UltraWiki: Ultra-fine-grained Entity Set Expansion with Negative Seed Entities

Autor: Li, Yangning, Lv, Qingsong, Yu, Tianyu, Li, Yinghui, Huang, Shulin, Lu, Tingwei, Hu, Xuming, JIang, Wenhao, Zheng, Hai-Tao, Wang, Hui

Entity Set Expansion (ESE) aims to identify new entities belonging to the same semantic class as a given set of seed entities. Traditional methods primarily relied on positive seed entities to represent a target semantic class, which poses challenge

Externí odkaz: http://arxiv.org/abs/2403.04247

Zobrazit plný text záznamu

Report

MESED: A Multi-modal Entity Set Expansion Dataset with Fine-grained Semantic Classes and Hard Negative Entities

Autor: Li, Yangning, Lu, Tingwei, Li, Yinghui, Yu, Tianyu, Huang, Shulin, Zheng, Hai-Tao, Zhang, Rui, Yuan, Jun

The Entity Set Expansion (ESE) task aims to expand a handful of seed entities with new entities belonging to the same semantic class. Conventional ESE methods are based on mono-modality (i.e., literal modality), which struggle to deal with complex en

Externí odkaz: http://arxiv.org/abs/2307.14878

Zobrazit plný text záznamu