Zobrazeno 1 - 10
of 277
pro vyhledávání: '"Wang, Zezhong"'
Autor:
Wang, Zezhong, Zeng, Xingshan, Liu, Weiwen, Wang, Yufei, Li, Liangyou, Wang, Yasheng, Shang, Lifeng, Jiang, Xin, Liu, Qun, Wong, Kam-Fai
Current research found the issue of Early Answering in large language models (LLMs), where the models already have an answer before generating the Chain-of-Thought (CoT). This phenomenon suggests a potential lack of necessary dependency between the p
Externí odkaz:
http://arxiv.org/abs/2406.16144
Storytelling is an ancient and precious human ability that has been rejuvenated in the digital age. Over the last decade, there has been a notable surge in the recognition and application of data storytelling, both in academia and industry. Recently,
Externí odkaz:
http://arxiv.org/abs/2404.01622
Autor:
Du, Yiming, Wang, Hongru, Zhao, Zhengyi, Liang, Bin, Wang, Baojun, Zhong, Wanjun, Wang, Zezhong, Wong, Kam-Fai
Long-term memory plays a critical role in personal interaction, considering long-term memory can better leverage world knowledge, historical information, and preferences in dialogues. Our research introduces PerLTQA, an innovative QA dataset that com
Externí odkaz:
http://arxiv.org/abs/2402.16288
The tendency of Large Language Models (LLMs) to generate hallucinations and exhibit overconfidence in predictions raises concerns regarding their reliability. Confidence or uncertainty estimations indicating the extent of trustworthiness of a model's
Externí odkaz:
http://arxiv.org/abs/2402.13606
Autor:
Wang, Hongru, Huang, Wenyu, Deng, Yang, Wang, Rui, Wang, Zezhong, Wang, Yufei, Mi, Fei, Pan, Jeff Z., Wong, Kam-Fai
Large Language Models (LLMs) has shown exceptional capabilities in many natual language understanding and generation tasks. However, the personalization issue still remains a much-coveted property, especially when it comes to the multiple sources inv
Externí odkaz:
http://arxiv.org/abs/2401.13256
Autor:
Wang, Zezhong, Yang, Fangkai, Wang, Lu, Zhao, Pu, Wang, Hongru, Chen, Liang, Lin, Qingwei, Wong, Kam-Fai
The jailbreak attack can bypass the safety measures of a Large Language Model (LLM), generating harmful content. This misuse of LLM has led to negative societal consequences. Currently, there are two main approaches to address jailbreak attacks: safe
Externí odkaz:
http://arxiv.org/abs/2310.15851
Autor:
Kwan, Wai-Chung, Wang, Huimin, Wang, Hongru, Wang, Zezhong, Wu, Xian, Zheng, Yefeng, Wong, Kam-Fai
Dialogue policy learning (DPL) is a crucial component of dialogue modelling. Its primary role is to determine the appropriate abstract response, commonly referred to as the "dialogue action". Traditional DPL methodologies have treated this as a seque
Externí odkaz:
http://arxiv.org/abs/2309.00230
Generating persona consistent dialogue response is important for developing an intelligent conversational agent. Recent works typically fine-tune large-scale pre-trained models on this task by concatenating persona texts and dialogue history as a sin
Externí odkaz:
http://arxiv.org/abs/2305.12782
Autor:
Wang, Hongru, Wang, Rui, Mi, Fei, Deng, Yang, Wang, Zezhong, Liang, Bin, Xu, Ruifeng, Wong, Kam-Fai
Large Language Models (LLMs), such as \texttt{ChatGPT}, greatly empower dialogue systems with strong language understanding and generation capabilities. However, most of the previous works prompt the LLMs to directly generate a response based on the
Externí odkaz:
http://arxiv.org/abs/2305.11792
Autor:
Yang, Fangkai, Zhao, Pu, Wang, Zezhong, Wang, Lu, Zhang, Jue, Garg, Mohit, Lin, Qingwei, Rajmohan, Saravan, Zhang, Dongmei
Large Language Model (LLM) has gained popularity and achieved remarkable results in open-domain tasks, but its performance in real industrial domain-specific scenarios is average due to its lack of specific domain knowledge. This issue has attracted
Externí odkaz:
http://arxiv.org/abs/2305.11541