Zobrazeno 1 - 10
of 3 786
pro vyhledávání: '"An, Ningyu"'
Model merging has become one of the key technologies for enhancing the capabilities and efficiency of Large Language Models (LLMs). However, our understanding of the expected performance gains and principles when merging any two models remains limite
Externí odkaz:
http://arxiv.org/abs/2410.12613
Autor:
Wang, Chenxi, Chen, Xiang, Zhang, Ningyu, Tian, Bozhong, Xu, Haoming, Deng, Shumin, Chen, Huajun
Multimodal Large Language Models (MLLMs) frequently exhibit hallucination phenomena, but the underlying reasons remain poorly understood. In this paper, we present an empirical analysis and find that, although MLLMs incorrectly generate the objects i
Externí odkaz:
http://arxiv.org/abs/2410.11779
Fine-tuning large language models (LLMs) on additional datasets is often necessary to optimize them for specific downstream tasks. However, existing safety alignment measures, which restrict harmful behavior during inference, are insufficient to miti
Externí odkaz:
http://arxiv.org/abs/2410.10343
Autor:
Qiao, Shuofei, Fang, Runnan, Qiu, Zhisong, Wang, Xiaobin, Zhang, Ningyu, Jiang, Yong, Xie, Pengjun, Huang, Fei, Chen, Huajun
Large Language Models (LLMs), with their exceptional ability to handle a wide range of tasks, have driven significant advancements in tackling reasoning and planning tasks, wherein decomposing complex problems into executable workflows is a crucial s
Externí odkaz:
http://arxiv.org/abs/2410.07869
Publikováno v:
A&A 690, A372 (2024)
We present a new constraint on the Galactic $^{12}$C/$^{13}$C gradient with sensitive HCO$^+$ absorption observations against strong continuum sources. The new measurements suffer less from beam dilution, optical depths, and chemical fractionation, a
Externí odkaz:
http://arxiv.org/abs/2409.11821
Autor:
Zhang, Ningyu, Xi, Zekun, Luo, Yujie, Wang, Peng, Tian, Bozhong, Yao, Yunzhi, Zhang, Jintian, Deng, Shumin, Sun, Mengshu, Liang, Lei, Zhang, Zhiqiang, Zhu, Xiaowei, Zhou, Jun, Chen, Huajun
Knowledge representation has been a central aim of AI since its inception. Symbolic Knowledge Graphs (KGs) and neural Large Language Models (LLMs) can both represent knowledge. KGs provide highly accurate and explicit knowledge representation, but fa
Externí odkaz:
http://arxiv.org/abs/2409.07497
While Large Language Models (LLMs) exhibit remarkable generative capabilities, they are not without flaws, particularly in the form of hallucinations. This issue is even more pronounced when LLMs are applied to specific languages and domains. For exa
Externí odkaz:
http://arxiv.org/abs/2409.05806
Autor:
Zhang, Jintian, Peng, Cheng, Sun, Mengshu, Chen, Xiang, Liang, Lei, Zhang, Zhiqiang, Zhou, Jun, Chen, Huajun, Zhang, Ningyu
Despite the recent advancements in Large Language Models (LLMs), which have significantly enhanced the generative capabilities for various NLP tasks, LLMs still face limitations in directly handling retrieval tasks. However, many practical applicatio
Externí odkaz:
http://arxiv.org/abs/2409.05152
Autor:
Wang, Xiaohan, Yang, Xiaoyan, Zhu, Yuqi, Shen, Yue, Wang, Jian, Wei, Peng, Liang, Lei, Gu, Jinjie, Chen, Huajun, Zhang, Ningyu
Large Language Models (LLMs) like GPT-4, MedPaLM-2, and Med-Gemini achieve performance competitively with human experts across various medical benchmarks. However, they still face challenges in making professional diagnoses akin to physicians, partic
Externí odkaz:
http://arxiv.org/abs/2408.12579
Autor:
He, Ningyu, Zhao, Zhehao, Guan, Hanqin, Wang, Jikai, Peng, Shuo, Li, Ding, Wang, Haoyu, Chen, Xiangqun, Guo, Yao
WebAssembly (Wasm), as a compact, fast, and isolation-guaranteed binary format, can be compiled from more than 40 high-level programming languages. However, vulnerabilities in Wasm binaries could lead to sensitive data leakage and even threaten their
Externí odkaz:
http://arxiv.org/abs/2408.08537