Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Qi, Zhenting"'
This paper introduces rStar, a self-play mutual reasoning approach that significantly improves reasoning capabilities of small language models (SLMs) without fine-tuning or superior models. rStar decouples reasoning into a self-play mutual generation
Externí odkaz:
http://arxiv.org/abs/2408.06195
Retrieval-Augmented Generation (RAG) improves pre-trained models by incorporating external knowledge at test time to enable customized adaptation. We study the risk of datastore leakage in Retrieval-In-Context RAG Language Models (LMs). We show that
Externí odkaz:
http://arxiv.org/abs/2402.17840
Instruction fine-tuning has conventionally been employed to adapt Large Language Models (LLMs) to a variety of tasks. Nonetheless, this technique often necessitates substantial computational resources, making it impractical for deployment by individu
Externí odkaz:
http://arxiv.org/abs/2312.05621
Autor:
Zhao, Yilun, Zhao, Chen, Nan, Linyong, Qi, Zhenting, Zhang, Wenlin, Tang, Xiangru, Mi, Boyu, Radev, Dragomir
Despite significant progress having been made in question answering on tabular data (Table QA), it's unclear whether, and to what extent existing Table QA models are robust to task-specific perturbations, e.g., replacing key question entities or shuf
Externí odkaz:
http://arxiv.org/abs/2306.14321
Autor:
Zhao, Yilun, Qi, Zhenting, Nan, Linyong, Mi, Boyu, Liu, Yixin, Zou, Weijin, Han, Simeng, Chen, Ruizhe, Tang, Xiangru, Xu, Yumo, Radev, Dragomir, Cohan, Arman
People primarily consult tables to conduct data analysis or answer specific questions. Text generation systems that can provide accurate table summaries tailored to users' information needs can facilitate more efficient access to relevant data insigh
Externí odkaz:
http://arxiv.org/abs/2305.14303
Logical Table-to-Text (LT2T) generation is tasked with generating logically faithful sentences from tables. There currently exists two challenges in the field: 1) Faithfulness: how to generate sentences that are factually correct given the table cont
Externí odkaz:
http://arxiv.org/abs/2302.02962
Reasoning over tabular data requires both table structure understanding and a broad set of table reasoning skills. Current models with table-specific architectures and pre-training methods perform well on understanding table structures, but they stil
Externí odkaz:
http://arxiv.org/abs/2210.12374
Fight detection in videos is an emerging deep learning application with today's prevalence of surveillance systems and streaming media. Previous work has largely relied on action recognition techniques to tackle this problem. In this paper, we propos
Externí odkaz:
http://arxiv.org/abs/2209.11477
Autor:
Han, Simeng, Schoelkopf, Hailey, Zhao, Yilun, Qi, Zhenting, Riddell, Martin, Zhou, Wenfei, Coady, James, Peng, David, Qiao, Yujie, Benson, Luke, Sun, Lucy, Wardle-Solano, Alex, Szabo, Hannah, Zubova, Ekaterina, Burtell, Matthew, Fan, Jonathan, Liu, Yixin, Wong, Brian, Sailor, Malcolm, Ni, Ansong, Nan, Linyong, Kasai, Jungo, Yu, Tao, Zhang, Rui, Fabbri, Alexander R., Kryscinski, Wojciech, Yavuz, Semih, Liu, Ye, Lin, Xi Victoria, Joty, Shafiq, Zhou, Yingbo, Xiong, Caiming, Ying, Rex, Cohan, Arman, Radev, Dragomir
Large language models (LLMs) have achieved remarkable performance on a variety of natural language understanding tasks. However, existing benchmarks are inadequate in measuring the complex logical reasoning capabilities of a model. We present FOLIO,
Externí odkaz:
http://arxiv.org/abs/2209.00840
Autor:
Zhao, Yilun, Qi, Zhenting, Nan, Linyong, Mi, Boyu, Liu, Yixin, Zou, Weijin, Han, Simeng, Tang, Xiangru, Xu, Yumo, Cohan, Arman, Radev, Dragomir
People primarily consult tables to conduct data analysis or answer specific questions. Text generation systems that can provide accurate table summaries tailored to users' information needs can facilitate more efficient access to relevant data insigh
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1d5c63d88345c37cd9fb6c41ce6c3718