Zobrazeno 1 - 10
of 385
pro vyhledávání: '"Wen, Jiaxin"'
Autor:
Wen, Jiaxin, Zhong, Ruiqi, Khan, Akbir, Perez, Ethan, Steinhardt, Jacob, Huang, Minlie, Bowman, Samuel R., He, He, Feng, Shi
Language models (LMs) can produce errors that are hard to detect for humans, especially when the task is complex. RLHF, the most popular post-training method, may exacerbate this problem: to achieve higher rewards, LMs might get better at convincing
Externí odkaz:
http://arxiv.org/abs/2409.12822
Despite the remarkable success of large language models (LLMs) on traditional natural language processing tasks, their planning ability remains a critical bottleneck in tackling complex multi-step reasoning tasks. Existing approaches mainly rely on p
Externí odkaz:
http://arxiv.org/abs/2409.12452
When using language models (LMs) to solve complex problems, humans might struggle to understand the LM-generated solutions and repair the flawed ones. To assist humans in repairing them, we propose to automatically decompose complex solutions into mu
Externí odkaz:
http://arxiv.org/abs/2406.04604
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
Pre-training on large-scale open-domain dialogue data can substantially improve the performance of dialogue models. However, the pre-trained dialogue model's ability to utilize long-range context is limited due to the scarcity of long-turn dialogue s
Externí odkaz:
http://arxiv.org/abs/2305.02606
Autor:
Chen, Mengting1 (AUTHOR), Wen, Jiaxin1 (AUTHOR), Qiu, Yiyan1,2 (AUTHOR), Gao, Xinyue1 (AUTHOR), Zhang, Jian1,3 (AUTHOR), Lin, Yifan1 (AUTHOR), Wu, Zekai1 (AUTHOR), Lin, Xiaohuang1 (AUTHOR), Zhu, An1,3 (AUTHOR) zhuan@fjmu.edu.cn
Publikováno v:
Toxins. Sep2024, Vol. 16 Issue 9, p375. 24p.
Recent studies have shown the impressive efficacy of counterfactually augmented data (CAD) for reducing NLU models' reliance on spurious features and improving their generalizability. However, current methods still heavily rely on human efforts or ta
Externí odkaz:
http://arxiv.org/abs/2211.16202
Autor:
Sabour, Sahand, Zhang, Wen, Xiao, Xiyao, Zhang, Yuwei, Zheng, Yinhe, Wen, Jiaxin, Zhao, Jialu, Huang, Minlie
The growing demand for mental health support has highlighted the importance of conversational agents as human supporters worldwide and in China. These agents could increase availability and reduce the relative costs of mental health support. The prov
Externí odkaz:
http://arxiv.org/abs/2209.10183
Endowing the protagonist with a specific personality is essential for writing an engaging story. In this paper, we aim to control the protagonist's persona in story generation, i.e., generating a story from a leading context and a persona description
Externí odkaz:
http://arxiv.org/abs/2204.10703
Autor:
Gu, Yuxian, Wen, Jiaxin, Sun, Hao, Song, Yi, Ke, Pei, Zheng, Chujie, Zhang, Zheng, Yao, Jianzhu, Liu, Lei, Zhu, Xiaoyan, Huang, Minlie
Large-scale pre-training has shown remarkable performance in building open-domain dialogue systems. However, previous works mainly focus on showing and evaluating the conversational performance of the released dialogue model, ignoring the discussion
Externí odkaz:
http://arxiv.org/abs/2203.09313