Zobrazeno 1 - 10
of 149
pro vyhledávání: '"Ma, Guangyuan"'
Autor:
Su, Zhenpeng, Wu, Xing, Lin, Zijia, Xiong, Yizhe, Lv, Minxuan, Ma, Guangyuan, Chen, Hui, Hu, Songlin, Ding, Guiguang
Large language models (LLM) have been attracting much attention from the community recently, due to their remarkable performance in all kinds of downstream tasks. According to the well-known scaling law, scaling up a dense LLM enhances its capabiliti
Externí odkaz:
http://arxiv.org/abs/2410.16077
Large Language Model-based Dense Retrieval (LLM-DR) optimizes over numerous heterogeneous fine-tuning collections from different domains. However, the discussion about its training data distribution is still minimal. Previous studies rely on empirica
Externí odkaz:
http://arxiv.org/abs/2408.10613
Autor:
Su, Zhenpeng, Lin, Zijia, Bai, Xue, Wu, Xing, Xiong, Yizhe, Lian, Haoran, Ma, Guangyuan, Chen, Hui, Ding, Guiguang, Zhou, Wei, Hu, Songlin
Scaling the size of a model enhances its capabilities but significantly increases computation complexity. Mixture-of-Experts models (MoE) address the issue by allowing model size to scale up without substantially increasing training or inference cost
Externí odkaz:
http://arxiv.org/abs/2407.09816
Masked auto-encoder pre-training has emerged as a prevalent technique for initializing and enhancing dense retrieval systems. It generally utilizes additional Transformer decoder blocks to provide sustainable supervision signals and compress contextu
Externí odkaz:
http://arxiv.org/abs/2401.11248
ChatGPT has garnered significant interest due to its impressive performance; however, there is growing concern about its potential risks, particularly in the detection of AI-generated content (AIGC), which is often challenging for untrained individua
Externí odkaz:
http://arxiv.org/abs/2309.02731
In this paper, we systematically study the potential of pre-training with Large Language Model(LLM)-based document expansion for dense passage retrieval. Concretely, we leverage the capabilities of LLMs for document expansion, i.e. query generation,
Externí odkaz:
http://arxiv.org/abs/2308.08285
Dialogue response selection aims to select an appropriate response from several candidates based on a given user and system utterance history. Most existing works primarily focus on post-training and fine-tuning tailored for cross-encoders. However,
Externí odkaz:
http://arxiv.org/abs/2306.04357
News recommendation aims to predict click behaviors based on user behaviors. How to effectively model the user representations is the key to recommending preferred news. Existing works are mostly focused on improvements in the supervised fine-tuning
Externí odkaz:
http://arxiv.org/abs/2304.12633
Passage retrieval aims to retrieve relevant passages from large collections of the open-domain corpus. Contextual Masked Auto-Encoding has been proven effective in representation bottleneck pre-training of a monolithic dual-encoder for passage retrie
Externí odkaz:
http://arxiv.org/abs/2304.10195
Growing techniques have been emerging to improve the performance of passage retrieval. As an effective representation bottleneck pretraining technique, the contextual masked auto-encoder utilizes contextual embedding to assist in the reconstruction o
Externí odkaz:
http://arxiv.org/abs/2304.03158