Zobrazeno 1 - 10
of 171
pro vyhledávání: '"Xu, Jinan"'
Chain-of-thought prompting significantly boosts the reasoning ability of large language models but still faces three issues: hallucination problem, restricted interpretability, and uncontrollable generation. To address these challenges, we present Ag
Externí odkaz:
http://arxiv.org/abs/2409.12411
Autor:
Zhang, Xintong, Lu, Di, Hu, Huiqi, Jiang, Nan, Yu, Xianhao, Xu, Jinan, Peng, Yujia, Li, Qing, Han, Wenjuan
Human cognition significantly influences expressed behavior and is intrinsically tied to authentic personality traits. Personality assessment plays a pivotal role in various fields, including psychology, education, social media, etc. However, traditi
Externí odkaz:
http://arxiv.org/abs/2407.19728
Gender bias has been a focal point in the study of bias in machine translation and language models. Existing machine translation gender bias evaluations are primarily focused on male and female genders, limiting the scope of the evaluation. To assess
Externí odkaz:
http://arxiv.org/abs/2407.16266
Although Large Language Models (LLMs) excel in NLP tasks, they still need external tools to extend their ability. Current research on tool learning with LLMs often assumes mandatory tool use, which does not always align with real-world situations, wh
Externí odkaz:
http://arxiv.org/abs/2407.12823
Knowledge distillation (KD) is known as a promising solution to compress large language models (LLMs) via transferring their knowledge to smaller models. During this process, white-box KD methods usually minimize the distance between the output distr
Externí odkaz:
http://arxiv.org/abs/2406.17328
Autor:
zhang, Xue, Liang, Yunlong, Meng, Fandong, Zhang, Songming, Chen, Yufeng, Xu, Jinan, Zhou, Jie
Multilingual knowledge editing (MKE) aims to simultaneously revise factual knowledge across multilingual languages within large language models (LLMs). However, most existing MKE methods just adapt existing monolingual editing methods to multilingual
Externí odkaz:
http://arxiv.org/abs/2406.16416
Autor:
Cheng, Ning, Guan, Changhao, Gao, Jing, Wang, Weihao, Li, You, Meng, Fandong, Zhou, Jie, Fang, Bin, Xu, Jinan, Han, Wenjuan
Touch holds a pivotal position in enhancing the perceptual and interactive capabilities of both humans and robots. Despite its significance, current tactile research mainly focuses on visual and tactile modalities, overlooking the language domain. In
Externí odkaz:
http://arxiv.org/abs/2406.03813
Recently, Knowledge Editing has received increasing attention, since it could update the specific knowledge from outdated ones in pretrained models without re-training. However, as pointed out by recent studies, existing related methods tend to merel
Externí odkaz:
http://arxiv.org/abs/2406.02882
Multilingual neural machine translation models generally distinguish translation directions by the language tag (LT) in front of the source or target sentences. However, current LT strategies cannot indicate the desired target language as expected on
Externí odkaz:
http://arxiv.org/abs/2406.02876
Fine-tuning large-scale pre-trained models is inherently a resource-intensive task. While it can enhance the capabilities of the model, it also incurs substantial computational costs, posing challenges to the practical application of downstream tasks
Externí odkaz:
http://arxiv.org/abs/2405.17357