Zobrazeno 1 - 10
of 153
pro vyhledávání: '"Zheng, Guoqing"'
Autor:
Mitra, Arindam, Del Corro, Luciano, Zheng, Guoqing, Mahajan, Shweti, Rouhana, Dany, Codas, Andres, Lu, Yadong, Chen, Wei-ge, Vrousgos, Olga, Rosset, Corby, Silva, Fillipe, Khanpour, Hamed, Lara, Yash, Awadallah, Ahmed
Synthetic data is becoming increasingly important for accelerating the development of language models, both large and small. Despite several successful use cases, researchers also raised concerns around model collapse and drawbacks of imitating other
Externí odkaz:
http://arxiv.org/abs/2407.03502
The remarkable abilities of large language models (LLMs) like GPT-4 partially stem from post-training processes like Reinforcement Learning from Human Feedback (RLHF) involving human preferences encoded in a reward model. However, these reward models
Externí odkaz:
http://arxiv.org/abs/2312.02206
Autor:
Mitra, Arindam, Del Corro, Luciano, Mahajan, Shweti, Codas, Andres, Simoes, Clarisse, Agarwal, Sahaj, Chen, Xuxi, Razdaibiedina, Anastasia, Jones, Erik, Aggarwal, Kriti, Palangi, Hamid, Zheng, Guoqing, Rosset, Corby, Khanpour, Hamed, Awadallah, Ahmed
Orca 1 learns from rich signals, such as explanation traces, allowing it to outperform conventional instruction-tuned models on benchmarks like BigBench Hard and AGIEval. In Orca 2, we continue exploring how improved training signals can enhance smal
Externí odkaz:
http://arxiv.org/abs/2311.11045
Autor:
Dun, Chen, Garcia, Mirian Hipolito, Zheng, Guoqing, Awadallah, Ahmed Hassan, Kyrillidis, Anastasios, Sim, Robert
Large Language Models (LLMs) have the ability to solve a variety of tasks, such as text summarization and mathematical questions, just out of the box, but they are often trained with a single task in mind. Due to high computational costs, the current
Externí odkaz:
http://arxiv.org/abs/2310.02842
Autor:
Xia, Menglin, Zhang, Xuchao, Couturier, Camille, Zheng, Guoqing, Rajmohan, Saravan, Ruhle, Victor
Retrieval augmentation enhances performance of traditional language models by incorporating additional context. However, the computational demands for retrieval augmented large language models (LLMs) pose a challenge when applying them to real-time t
Externí odkaz:
http://arxiv.org/abs/2308.04215
Autor:
Dun, Chen, Garcia, Mirian Hipolito, Zheng, Guoqing, Awadallah, Ahmed Hassan, Sim, Robert, Kyrillidis, Anastasios, Dimitriadis, Dimitrios
One of the goals in Federated Learning (FL) is to create personalized models that can adapt to the context of each participating client, while utilizing knowledge from a shared global model. Yet, often, personalization requires a fine-tuning step usi
Externí odkaz:
http://arxiv.org/abs/2306.08586
Publikováno v:
Zhongguo youzhi, Vol 49, Iss 8, Pp 103-110 (2024)
旨在为芝麻产业发展提供文献支撑,利用CiteSpace及Excel软件,基于2012—2022年Web of Science(WoS)核心合集数据库和中国知网(CNKI)学术期刊数据库中的中文核心期刊,采用文献计量方法对芝麻研
Externí odkaz:
https://doaj.org/article/9decc49f8fd9445f99f26878db927d7b
Recent work has shown that language models (LMs) trained with multi-task \textit{instructional learning} (MTIL) can solve diverse NLP tasks in zero- and few-shot settings with improved performance compared to prompt tuning. MTIL illustrates that LMs
Externí odkaz:
http://arxiv.org/abs/2210.11617
The success of graph neural networks on graph-based web mining highly relies on abundant human-annotated data, which is laborious to obtain in practice. When only few labeled nodes are available, how to improve their robustness is a key to achieve re
Externí odkaz:
http://arxiv.org/abs/2208.12422
Existing works on anomaly detection (AD) rely on clean labels from human annotators that are expensive to acquire in practice. In this work, we propose a method to leverage weak/noisy labels (e.g., risk scores generated by machine rules for detecting
Externí odkaz:
http://arxiv.org/abs/2208.11290