Zobrazeno 1 - 10
of 30 078
pro vyhledávání: '"Xu,Jun"'
In legal practice, judges apply the trichotomous dogmatics of criminal law, sequentially assessing the elements of the offense, unlawfulness, and culpability to determine whether an individual's conduct constitutes a crime. Although current legal lar
Externí odkaz:
http://arxiv.org/abs/2412.14588
In this paper, we propose CitaLaw, the first benchmark designed to evaluate LLMs' ability to produce legally sound responses with appropriate citations. CitaLaw features a diverse set of legal questions for both laypersons and practitioners, paired w
Externí odkaz:
http://arxiv.org/abs/2412.14556
In search scenarios, user experience can be hindered by erroneous queries due to typos, voice errors, or knowledge gaps. Therefore, query correction is crucial for search engines. Current correction models, usually small models trained on specific da
Externí odkaz:
http://arxiv.org/abs/2412.12701
Greybox fuzzing has emerged as a preferred technique for discovering software bugs, striking a balance between efficiency and depth of exploration. While research has focused on improving fuzzing techniques, the importance of high-quality initial see
Externí odkaz:
http://arxiv.org/abs/2411.18143
Publikováno v:
Physical Review C 110, 054613 (2024)
Inspired by various studies on extracting the density distributions of nuclei from their collisions at ultrarelativistic energies, in the present work we investigate the possibility of extracting the neutron-skin thickness $\Delta r_{np}$ in nuclei b
Externí odkaz:
http://arxiv.org/abs/2411.08337
Deep learning has excelled in medical image classification, but its clinical application is limited by poor interpretability. Capsule networks, known for encoding hierarchical relationships and spatial features, show potential in addressing this issu
Externí odkaz:
http://arxiv.org/abs/2411.01564
Text embeddings enable various applications, but their performance deteriorates on longer texts. In this paper, we find that the performance degradation is due to a phenomenon called Length Collapse, where longer text embeddings collapse into a narro
Externí odkaz:
http://arxiv.org/abs/2410.24200
Autor:
Sun, Zhongxiang, Zang, Xiaoxue, Zheng, Kai, Song, Yang, Xu, Jun, Zhang, Xiao, Yu, Weijie, Li, Han
Retrieval-Augmented Generation (RAG) models are designed to incorporate external knowledge, reducing hallucinations caused by insufficient parametric (internal) knowledge. However, even with accurate and relevant retrieved content, RAG models can sti
Externí odkaz:
http://arxiv.org/abs/2410.11414
Recent research on query generation has focused on using Large Language Models (LLMs), which despite bringing state-of-the-art performance, also introduce issues with hallucinations in the generated queries. In this work, we introduce relevance hallu
Externí odkaz:
http://arxiv.org/abs/2410.11366
Autor:
Qu, Changle, Dai, Sunhao, Wei, Xiaochi, Cai, Hengyi, Wang, Shuaiqiang, Yin, Dawei, Xu, Jun, Wen, Ji-Rong
Tool learning enables Large Language Models (LLMs) to interact with external environments by invoking tools, serving as an effective strategy to mitigate the limitations inherent in their pre-training data. In this process, tool documentation plays a
Externí odkaz:
http://arxiv.org/abs/2410.08197