Zobrazeno 31 - 40
of 365
pro vyhledávání: '"Huang, Minlie"'
Autor:
Zhang, Zhexin, Lei, Leqi, Wu, Lindong, Sun, Rui, Huang, Yongkang, Long, Chong, Liu, Xiao, Lei, Xuanyu, Tang, Jie, Huang, Minlie
With the rapid development of Large Language Models (LLMs), increasing attention has been paid to their safety concerns. Consequently, evaluating the safety of LLMs has become an essential task for facilitating the broad applications of LLMs. Neverth
Externí odkaz:
http://arxiv.org/abs/2309.07045
Multiple choice questions (MCQs) serve as a common yet important task format in the evaluation of large language models (LLMs). This work shows that modern LLMs are vulnerable to option position changes in MCQs due to their inherent "selection bias",
Externí odkaz:
http://arxiv.org/abs/2309.03882
Autor:
Liu, Xiao, Yu, Hao, Zhang, Hanchen, Xu, Yifan, Lei, Xuanyu, Lai, Hanyu, Gu, Yu, Ding, Hangliang, Men, Kaiwen, Yang, Kejuan, Zhang, Shudan, Deng, Xiang, Zeng, Aohan, Du, Zhengxiao, Zhang, Chenhui, Shen, Sheng, Zhang, Tianjun, Su, Yu, Sun, Huan, Huang, Minlie, Dong, Yuxiao, Tang, Jie
Large Language Models (LLMs) are becoming increasingly smart and autonomous, targeting real-world pragmatic missions beyond traditional NLP tasks. As a result, there has been an urgent need to evaluate LLMs as agents on challenging tasks in interacti
Externí odkaz:
http://arxiv.org/abs/2308.03688
Emotional support conversation (ESC) aims to provide emotional support (ES) to improve one's mental state. Existing works stay at fitting grounded responses and responding strategies (e.g., question), which ignore the effect on ES and lack explicit g
Externí odkaz:
http://arxiv.org/abs/2307.07994
Existing evaluation metrics for natural language generation (NLG) tasks face the challenges on generalization ability and interpretability. Specifically, most of the well-performed metrics are required to train on evaluation datasets of specific NLG
Externí odkaz:
http://arxiv.org/abs/2307.06869
Large pre-trained language models achieve impressive results across many tasks. However, recent works point out that pre-trained language models may memorize a considerable fraction of their training data, leading to the privacy risk of information l
Externí odkaz:
http://arxiv.org/abs/2307.04401
Autor:
Guan, Jian, Huang, Minlie
Despite the huge progress in myriad generation tasks, pretrained language models (LMs) such as GPT2 still tend to generate repetitive texts with maximization-based decoding algorithms for open-ended generation. We attribute their overestimation of to
Externí odkaz:
http://arxiv.org/abs/2307.01542
Knowledge Distillation (KD) is a promising technique for reducing the high computational demand of large language models (LLMs). However, previous KD methods are primarily applied to white-box classification models or training small models to imitate
Externí odkaz:
http://arxiv.org/abs/2306.08543
As a main field of artificial intelligence, natural language processing (NLP) has achieved remarkable success via deep neural networks. Plenty of NLP tasks have been addressed in a unified manner, with various tasks being associated with each other t
Externí odkaz:
http://arxiv.org/abs/2306.04459
It has always been an important yet challenging problem to control language models to avoid generating texts with undesirable attributes, such as toxic language and unnatural repetition. We introduce Click for controllable text generation, which need
Externí odkaz:
http://arxiv.org/abs/2306.03350