Zobrazeno 1 - 10
of 218
pro vyhledávání: '"Xiong, Deyi"'
Autor:
Leng, Yongqi, Xiong, Deyi
While large language models (LLMs) have demonstrated superior multi-task capabilities, understanding the learning mechanisms behind this is still a challenging problem. In this paper, we attempt to understand such mechanisms from the perspective of n
Externí odkaz:
http://arxiv.org/abs/2407.06488
Autor:
Li, Zhigen, Peng, Jianxiang, Wang, Yanmeng, Shen, Tianhao, Zhang, Minghui, Su, Linxi, Wu, Shang, Wu, Yihang, Wang, Yuqian, Wang, Ye, Hu, Wei, Li, Jianfeng, Wang, Shaojun, Xiao, Jing, Xiong, Deyi
Controllability and proactivity are crucial properties of autonomous conversational agents (CAs). Controllability requires the CAs to follow the standard operating procedures (SOPs), such as verifying identity before activating credit cards. Proactiv
Externí odkaz:
http://arxiv.org/abs/2407.03884
Manual Red teaming is a commonly-used method to identify vulnerabilities in large language models (LLMs), which, is costly and unscalable. In contrast, automated red teaming uses a Red LLM to automatically generate adversarial prompts to the Target L
Externí odkaz:
http://arxiv.org/abs/2407.03876
It is widely acknowledged that large language models (LLMs) encode a vast reservoir of knowledge after being trained on mass data. Recent studies disclose knowledge conflicts in LLM generation, wherein outdated or incorrect parametric knowledge (i.e.
Externí odkaz:
http://arxiv.org/abs/2406.18406
The advent of large language models (LLMs) has predominantly catered to high-resource languages, leaving a disparity in performance for low-resource languages. Conventional Continual Training (CT) approaches to bridge this gap often undermine a model
Externí odkaz:
http://arxiv.org/abs/2407.00875
Large language models (LLMs) exhibit outstanding performance in machine translation via in-context learning. In contrast to sentence-level translation, document-level translation (DOCMT) by LLMs based on in-context learning faces two major challenges
Externí odkaz:
http://arxiv.org/abs/2406.07081
Autor:
Shi, Ling, Xiong, Deyi
Large language models (LLMs) are possessed of numerous beneficial capabilities, yet their potential inclination harbors unpredictable risks that may materialize in the future. We hence propose CRiskEval, a Chinese dataset meticulously designed for ga
Externí odkaz:
http://arxiv.org/abs/2406.04752
Autor:
Lee, Andrew H., Semnani, Sina J., Castillo-López, Galo, de Chalendar, Gäel, Choudhury, Monojit, Dua, Ashna, Kavitha, Kapil Rajesh, Kim, Sungkyun, Kodali, Prashant, Kumaraguru, Ponnurangam, Lombard, Alexis, Moradshahi, Mehrad, Park, Gihyun, Semmar, Nasredine, Seo, Jiwon, Shen, Tianhao, Shrivastava, Manish, Xiong, Deyi, Lam, Monica S.
Creating multilingual task-oriented dialogue (TOD) agents is challenging due to the high cost of training data acquisition. Following the research trend of improving training data efficiency, we show for the first time, that in-context learning is su
Externí odkaz:
http://arxiv.org/abs/2405.17840
Autor:
Sun, Chenxi, Zhang, Hongzhi, Lin, Zijia, Zhang, Jingyuan, Zhang, Fuzheng, Wang, Zhongyuan, Chen, Bin, Song, Chengru, Zhang, Di, Gai, Kun, Xiong, Deyi
Large language models have demonstrated exceptional capability in natural language understanding and generation. However, their generation speed is limited by the inherently sequential nature of their decoding process, posing challenges for real-time
Externí odkaz:
http://arxiv.org/abs/2405.15208
Ensuring large language models (LLM) behave consistently with human goals, values, and intentions is crucial for their safety but yet computationally expensive. To reduce the computational cost of alignment training of LLMs, especially for those with
Externí odkaz:
http://arxiv.org/abs/2405.13578