Zobrazeno 1 - 10
of 413
pro vyhledávání: '"Zhai Chengxiang"'
Large language models (LLMs) are known to struggle with complicated reasoning tasks such as math word problems (MWPs). In this paper, we present how analogy from similarly structured questions can improve LLMs' problem-solving capabilities for MWPs.
Externí odkaz:
http://arxiv.org/abs/2411.16454
Autor:
Breuer, Timo, Kreutz, Christin Katharina, Fuhr, Norbert, Balog, Krisztian, Schaer, Philipp, Bernard, Nolwenn, Frommholz, Ingo, Gohsen, Marcel, Ji, Kaixin, Jones, Gareth J. F., Keller, Jüri, Liu, Jiqun, Mladenov, Martin, Pasi, Gabriella, Trippas, Johanne, Wang, Xi, Zerhoudi, Saber, Zhai, ChengXiang
This paper is a report of the Workshop on Simulations for Information Access (Sim4IA) workshop at SIGIR 2024. The workshop had two keynotes, a panel discussion, nine lightning talks, and two breakout sessions. Key takeaways were user simulation's imp
Externí odkaz:
http://arxiv.org/abs/2409.18024
Autor:
Pi, Xinyu, Wu, Mingyuan, Jiang, Jize, Zheng, Haozhen, Tian, Beitong, Zhai, Chengxiang, Nahrstedt, Klara, Hu, Zhiting
Smaller-scale Vision-Langauge Models (VLMs) often claim to perform on par with larger models in general-domain visual grounding and question-answering benchmarks while offering advantages in computational efficiency and storage. However, their abilit
Externí odkaz:
http://arxiv.org/abs/2407.18391
Autor:
Mehrdad, Navid, Mohapatra, Hrushikesh, Bagdouri, Mossaab, Chandran, Prijith, Magnani, Alessandro, Cai, Xunfan, Puthenputhussery, Ajit, Yadav, Sachin, Lee, Tony, Zhai, ChengXiang, Liao, Ciya
High relevance of retrieved and re-ranked items to the search query is the cornerstone of successful product search, yet measuring relevance of items to queries is one of the most challenging tasks in product information retrieval, and quality of pro
Externí odkaz:
http://arxiv.org/abs/2406.00247
Autor:
Sun, Chenkai, Yang, Ke, Reddy, Revanth Gangi, Fung, Yi R., Chan, Hou Pong, Small, Kevin, Zhai, ChengXiang, Ji, Heng
The increasing demand for personalized interactions with large language models (LLMs) calls for methodologies capable of accurately and efficiently identifying user opinions and preferences. Retrieval augmentation emerges as an effective strategy, as
Externí odkaz:
http://arxiv.org/abs/2402.11060
Autor:
Zhang, Yu, Zhang, Yunyi, Shen, Yanzhen, Deng, Yu, Popa, Lucian, Shwartz, Larisa, Zhai, ChengXiang, Han, Jiawei
Accurately typing entity mentions from text segments is a fundamental task for various natural language processing applications. Many previous approaches rely on massive human-annotated data to perform entity typing. Nevertheless, collecting such dat
Externí odkaz:
http://arxiv.org/abs/2401.13129
Autor:
Yang, Ke, Liu, Jiateng, Wu, John, Yang, Chaoqi, Fung, Yi R., Li, Sha, Huang, Zixuan, Cao, Xu, Wang, Xingyao, Wang, Yiquan, Ji, Heng, Zhai, Chengxiang
The prominent large language models (LLMs) of today differ from past language models not only in size, but also in the fact that they are trained on a combination of natural language and formal language (code). As a medium between humans and computer
Externí odkaz:
http://arxiv.org/abs/2401.00812
Autor:
Reddy, Revanth Gangi, Bai, Hao, Yao, Wentao, Suresh, Sharath Chandra Etagi, Ji, Heng, Zhai, ChengXiang
Open-domain dialog involves generating search queries that help obtain relevant knowledge for holding informative conversations. However, it can be challenging to determine what information to retrieve when the user is passive and does not express a
Externí odkaz:
http://arxiv.org/abs/2310.14340
Autor:
Sun, Chenkai, Li, Jinning, Fung, Yi R., Chan, Hou Pong, Abdelzaher, Tarek, Zhai, ChengXiang, Ji, Heng
Automatic response forecasting for news media plays a crucial role in enabling content producers to efficiently predict the impact of news releases and prevent unexpected negative outcomes such as social conflict and moral injury. To effectively fore
Externí odkaz:
http://arxiv.org/abs/2310.13297