Zobrazeno 1 - 10
of 1 074
pro vyhledávání: '"He Xiaofeng"'
Model editing aims to correct outdated or erroneous knowledge in large models without costly retraining. Recent research discovered that the mid-layer representation of the subject's final token in a prompt has a strong influence on factual predictio
Externí odkaz:
http://arxiv.org/abs/2408.09916
KEHRL: Learning Knowledge-Enhanced Language Representations with Hierarchical Reinforcement Learning
Knowledge-enhanced pre-trained language models (KEPLMs) leverage relation triples from knowledge graphs (KGs) and integrate these external data sources into language models via self-supervised learning. Previous works treat knowledge enhancement as t
Externí odkaz:
http://arxiv.org/abs/2406.16374
Autor:
Li, Dongyang, Zhang, Taolin, Deng, Jiali, Huang, Longtao, Wang, Chengyu, He, Xiaofeng, Xue, Hui
Cross-lingual representation learning transfers knowledge from resource-rich data to resource-scarce ones to improve the semantic understanding abilities of different languages. However, previous works rely on shallow unsupervised data generated by t
Externí odkaz:
http://arxiv.org/abs/2406.16372
Autor:
Li, Dongyang, Yan, Junbing, Zhang, Taolin, Wang, Chengyu, He, Xiaofeng, Huang, Longtao, Xue, Hui, Huang, Jun
Retrieval augmented generation (RAG) exhibits outstanding performance in promoting the knowledge capabilities of large language models (LLMs) with retrieved documents related to user queries. However, RAG only focuses on improving the response qualit
Externí odkaz:
http://arxiv.org/abs/2406.16367
Autor:
Zhang, Taolin, Chen, Qizhou, Li, Dongyang, Wang, Chengyu, He, Xiaofeng, Huang, Longtao, Xue, Hui, Huang, Jun
Recently, while large language models (LLMs) have demonstrated impressive results, they still suffer from hallucination, i.e., the generation of false information. Model editing is the task of fixing factual mistakes in LLMs; yet, most previous works
Externí odkaz:
http://arxiv.org/abs/2405.20588
Autor:
Chen, Qizhou, Zhang, Taolin, He, Xiaofeng, Li, Dongyang, Wang, Chengyu, Huang, Longtao, Xue, Hui
Publikováno v:
EMNLP 2024 main
Model editing aims to correct outdated or erroneous knowledge in large language models (LLMs) without the need for costly retraining. Lifelong model editing is the most challenging task that caters to the continuous editing requirements of LLMs. Prio
Externí odkaz:
http://arxiv.org/abs/2405.03279
Autor:
Zhang, Taolin, Li, Dongyang, Chen, Qizhou, Wang, Chengyu, Huang, Longtao, Xue, Hui, He, Xiaofeng, Huang, Jun
Retrieval-augmented large language models (LLMs) leverage relevant content retrieved by information retrieval systems to generate correct responses, aiming to alleviate the hallucination problem. However, existing retriever-responder methods typicall
Externí odkaz:
http://arxiv.org/abs/2405.02659
The black-box nature of deep learning models in NLP hinders their widespread application. The research focus has shifted to Hierarchical Attribution (HA) for its ability to model feature interactions. Recent works model non-contiguous combinations wi
Externí odkaz:
http://arxiv.org/abs/2403.16554
Autor:
Yan, Junbing, Wang, Chengyu, Zhang, Taolin, He, Xiaofeng, Huang, Jun, Huang, Longtao, Xue, Hui, Zhang, Wei
KEPLMs are pre-trained models that utilize external knowledge to enhance language understanding. Previous language models facilitated knowledge acquisition by incorporating knowledge-related pre-training tasks learned from relation triples in knowled
Externí odkaz:
http://arxiv.org/abs/2403.11203
Autor:
Qu, Hao, Zhang, Lilian, Mao, Jun, Tie, Junbo, He, Xiaofeng, Hu, Xiaoping, Shi, Yifei, Chen, Changhao
The performance of visual SLAM in complex, real-world scenarios is often compromised by unreliable feature extraction and matching when using handcrafted features. Although deep learning-based local features excel at capturing high-level information
Externí odkaz:
http://arxiv.org/abs/2401.09160