Zobrazeno 1 - 10
of 206
pro vyhledávání: '"Chi, Ed H."'
Autor:
Tsai, Alicia Y., Kraft, Adam, Jin, Long, Cai, Chenwei, Hosseini, Anahita, Xu, Taibai, Zhang, Zemin, Hong, Lichan, Chi, Ed H., Yi, Xinyang
Recent advancements have showcased the potential of Large Language Models (LLMs) in executing reasoning tasks, particularly facilitated by Chain-of-Thought (CoT) prompting. While tasks like arithmetic reasoning involve clear, definitive answers and l
Externí odkaz:
http://arxiv.org/abs/2408.00802
Autor:
Zheng, Huaixiu Steven, Mishra, Swaroop, Zhang, Hugh, Chen, Xinyun, Chen, Minmin, Nova, Azade, Hou, Le, Cheng, Heng-Tze, Le, Quoc V., Chi, Ed H., Zhou, Denny
We introduce NATURAL PLAN, a realistic planning benchmark in natural language containing 3 key tasks: Trip Planning, Meeting Planning, and Calendar Scheduling. We focus our evaluation on the planning capabilities of LLMs with full information on the
Externí odkaz:
http://arxiv.org/abs/2406.04520
Autor:
Wang, Yuyan, Banerjee, Cheenar, Chucri, Samer, Soldo, Fabio, Badam, Sriraj, Chi, Ed H., Chen, Minmin
Recommender systems that overly focus on short-term engagement prevents users from exploring diverse interests. To tackle this challenge, numerous diversification algorithms have been proposed. These algorithms typically rely on measures of item simi
Externí odkaz:
http://arxiv.org/abs/2405.12327
Autor:
Cao, Yuwei, Mehta, Nikhil, Yi, Xinyang, Keshavan, Raghunandan, Heldt, Lukasz, Hong, Lichan, Chi, Ed H., Sathiamoorthy, Maheswaran
Large language models (LLMs) have recently been used as backbones for recommender systems. However, their performance often lags behind conventional methods in standard tasks like retrieval. We attribute this to a mismatch between LLMs' knowledge and
Externí odkaz:
http://arxiv.org/abs/2404.00245
Autor:
Liu, Zichang, Liu, Qingyun, Li, Yuening, Liu, Liang, Shrivastava, Anshumali, Bi, Shuchao, Hong, Lichan, Chi, Ed H., Zhao, Zhe
Recent advancements in foundation models have yielded impressive performance across a wide range of tasks. Meanwhile, for specific applications, practitioners have been developing specialized application models. To enjoy the benefits of both kinds of
Externí odkaz:
http://arxiv.org/abs/2402.14035
Autor:
Sachdeva, Noveen, Coleman, Benjamin, Kang, Wang-Cheng, Ni, Jianmo, Hong, Lichan, Chi, Ed H., Caverlee, James, McAuley, Julian, Cheng, Derek Zhiyuan
The training of large language models (LLMs) is expensive. In this paper, we study data-efficient approaches for pre-training LLMs, i.e., techniques that aim to optimize the Pareto frontier of model quality and training resource/data consumption. We
Externí odkaz:
http://arxiv.org/abs/2402.09668
Autor:
Roh, Yuji, Liu, Qingyun, Gui, Huan, Yuan, Zhe, Tang, Yujin, Whang, Steven Euijong, Liu, Liang, Bi, Shuchao, Hong, Lichan, Chi, Ed H., Zhao, Zhe
Fine-tuning is becoming widely used for leveraging the power of pre-trained foundation models in new downstream tasks. While there are many successes of fine-tuning on various tasks, recent studies have observed challenges in the generalization of fi
Externí odkaz:
http://arxiv.org/abs/2402.04644
Autor:
Zhou, Pei, Pujara, Jay, Ren, Xiang, Chen, Xinyun, Cheng, Heng-Tze, Le, Quoc V., Chi, Ed H., Zhou, Denny, Mishra, Swaroop, Zheng, Huaixiu Steven
We introduce SELF-DISCOVER, a general framework for LLMs to self-discover the task-intrinsic reasoning structures to tackle complex reasoning problems that are challenging for typical prompting methods. Core to the framework is a self-discovery proce
Externí odkaz:
http://arxiv.org/abs/2402.03620
Autor:
Gui, Huan, Wang, Ruoxi, Yin, Ke, Jin, Long, Kula, Maciej, Xu, Taibai, Hong, Lichan, Chi, Ed H.
Learning feature interaction is the critical backbone to building recommender systems. In web-scale applications, learning feature interaction is extremely challenging due to the sparse and large input feature space; meanwhile, manually crafting effe
Externí odkaz:
http://arxiv.org/abs/2311.05884
Autor:
Zheng, Huaixiu Steven, Mishra, Swaroop, Chen, Xinyun, Cheng, Heng-Tze, Chi, Ed H., Le, Quoc V, Zhou, Denny
We present Step-Back Prompting, a simple prompting technique that enables LLMs to do abstractions to derive high-level concepts and first principles from instances containing specific details. Using the concepts and principles to guide reasoning, LLM
Externí odkaz:
http://arxiv.org/abs/2310.06117