Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Zhong, Zexuan"'
Autor:
Xiao, Chaojun, Zhang, Zhengyan, Song, Chenyang, Jiang, Dazhi, Yao, Feng, Han, Xu, Wang, Xiaozhi, Wang, Shuo, Huang, Yufei, Lin, Guanyu, Chen, Yingfa, Zhao, Weilin, Tu, Yuge, Zhong, Zexuan, Zhang, Ao, Si, Chenglei, Moo, Khai Hao, Zhao, Chenyang, Chen, Huimin, Lin, Yankai, Liu, Zhiyuan, Shang, Jingbo, Sun, Maosong
Advancements in LLMs have recently unveiled challenges tied to computational efficiency and continual scalability due to their requirements of huge parameters, making the applications and evolution of these models on devices with limited computation
Externí odkaz:
http://arxiv.org/abs/2409.02877
Retrieval-augmented generation (RAG) has been shown vulnerable to retrieval corruption attacks: an attacker can inject malicious passages into retrieval results to induce inaccurate responses. In this paper, we propose RobustRAG as the first defense
Externí odkaz:
http://arxiv.org/abs/2405.15556
Mixture-of-experts (MoE) models facilitate efficient scaling; however, training the router network introduces the challenge of optimizing a non-differentiable, discrete objective. Recently, a fully-differentiable MoE architecture, SMEAR, was proposed
Externí odkaz:
http://arxiv.org/abs/2405.03133
Autor:
Asai, Akari, Zhong, Zexuan, Chen, Danqi, Koh, Pang Wei, Zettlemoyer, Luke, Hajishirzi, Hannaneh, Yih, Wen-tau
Parametric language models (LMs), which are trained on vast amounts of web data, exhibit remarkable flexibility and capability. However, they still face practical challenges such as hallucinations, difficulty in adapting to new data distributions, an
Externí odkaz:
http://arxiv.org/abs/2403.03187
We introduce Retrieval-Based Speculative Decoding (REST), a novel algorithm designed to speed up language model generation. The key insight driving the development of REST is the observation that the process of text generation often includes certain
Externí odkaz:
http://arxiv.org/abs/2311.08252
Dense retrievers have achieved state-of-the-art performance in various information retrieval tasks, but to what extent can they be safely deployed in real-world applications? In this work, we propose a novel attack for dense retrieval systems in whic
Externí odkaz:
http://arxiv.org/abs/2310.19156
Retrieval-based language models (LMs) have demonstrated improved interpretability, factuality, and adaptability compared to their parametric counterparts, by incorporating retrieved text from external datastores. While it is well known that parametri
Externí odkaz:
http://arxiv.org/abs/2305.14888
The information stored in large language models (LLMs) falls out of date quickly, and retraining from scratch is often not an option. This has recently given rise to a range of techniques for injecting new facts through updating model weights. Curren
Externí odkaz:
http://arxiv.org/abs/2305.14795
Fine-tuning a language model on a new domain is standard practice for domain adaptation. However, it can be infeasible when it comes to modern large-scale language models such as GPT-3, which can only be accessed through APIs, making it difficult to
Externí odkaz:
http://arxiv.org/abs/2302.10879
Recent work has improved language models (LMs) remarkably by equipping them with a non-parametric memory component. However, most existing approaches only introduce mem-ories at testing time or represent them using a separately trained encoder, resul
Externí odkaz:
http://arxiv.org/abs/2205.12674