Zobrazeno 1 - 10
of 74
pro vyhledávání: '"Liu, Aiwei"'
Ensuring that Multimodal Large Language Models (MLLMs) maintain consistency in their responses is essential for developing trustworthy multimodal intelligence. However, existing benchmarks include many samples where all MLLMs \textit{exhibit high res
Externí odkaz:
http://arxiv.org/abs/2411.02708
Fine-tuning Large Language Models (LLMs) has become a crucial technique for adapting pre-trained models to downstream tasks. However, the enormous size of LLMs poses significant challenges in terms of computational complexity and resource requirement
Externí odkaz:
http://arxiv.org/abs/2410.19694
Multimodal Large Language Models (MLLMs) have emerged as a central focus in both industry and academia, but often suffer from biases introduced by visual and language priors, which can lead to multimodal hallucination. These biases arise from the vis
Externí odkaz:
http://arxiv.org/abs/2410.04780
Autor:
Yu, Dianzhi, Zhang, Xinni, Chen, Yankai, Liu, Aiwei, Zhang, Yifei, Yu, Philip S., King, Irwin
Continual learning (CL) aims to empower machine learning models to learn continually from new data, while building upon previously acquired knowledge without forgetting. As machine learning models have evolved from small to large pre-trained architec
Externí odkaz:
http://arxiv.org/abs/2410.05352
Autor:
Liu, Aiwei, Bai, Haoping, Lu, Zhiyun, Sun, Yanchao, Kong, Xiang, Wang, Simon, Shan, Jiulong, Jose, Albin Madappally, Liu, Xiaojiang, Wen, Lijie, Yu, Philip S., Cao, Meng
Direct Preference Optimization (DPO) has been widely adopted for preference alignment of Large Language Models (LLMs) due to its simplicity and effectiveness. However, DPO is derived as a bandit problem in which the whole response is treated as a sin
Externí odkaz:
http://arxiv.org/abs/2410.04350
Autor:
Liu, Aiwei, Guan, Sheng, Liu, Yiming, Pan, Leyi, Zhang, Yifei, Fang, Liancheng, Wen, Lijie, Yu, Philip S., Hu, Xuming
Text watermarking for Large Language Models (LLMs) has made significant progress in detecting LLM outputs and preventing misuse. Current watermarking techniques offer high detectability, minimal impact on text quality, and robustness to text editing.
Externí odkaz:
http://arxiv.org/abs/2410.03168
Autor:
Gao, Zitian, Niu, Boye, He, Xuzheng, Xu, Haotian, Liu, Hongzhang, Liu, Aiwei, Hu, Xuming, Wen, Lijie
We propose SC-MCTS*: a novel Monte Carlo Tree Search (MCTS) reasoning algorithm for Large Language Models (LLMs), significantly improves both reasoning accuracy and speed. Our motivation comes from: 1. Previous MCTS LLM reasoning works often overlook
Externí odkaz:
http://arxiv.org/abs/2410.01707
Autor:
Pan, Leyi, Liu, Aiwei, Lu, Yijian, Gao, Zitian, Di, Yichen, Wen, Lijie, King, Irwin, Yu, Philip S.
Watermarking algorithms for large language models (LLMs) have attained high accuracy in detecting LLM-generated text. However, existing methods primarily focus on distinguishing fully watermarked text from non-watermarked text, overlooking real-world
Externí odkaz:
http://arxiv.org/abs/2409.05112
Augmenting Large Language Models (LLMs) with retrieved external knowledge has proven effective for improving the factual accuracy of generated responses. Despite their success, retrieval-augmented LLMs still face the distractibility issue, where the
Externí odkaz:
http://arxiv.org/abs/2406.17519
Large Language Models (LLMs) are limited by their parametric knowledge, leading to hallucinations in knowledge-extensive tasks. To address this, Retrieval-Augmented Generation (RAG) incorporates external document chunks to expand LLM knowledge. Furth
Externí odkaz:
http://arxiv.org/abs/2406.11357