Tenofovir versus entecavir for children and adults with chronic hepatitis B

Li, Meixuan; Yao, Liang; Qin, Yu; Li, Yanfei; Lu, Mengying; Ma, Mina; Yang, Minyan; Guo, Ke; Wang, Qi; Zhang, Zhichun; Zhu, LongDong; Li, Xiuxia; Yang, Kehu

doi:10.1002/14651858.cd015642

Cited by 1 publication

(1 citation statement)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing KE techniques for pre-trained LLMs focus on updating the parameters of LLMs to reflect these updates [10,[14][15][16]. Since such parametric updates are computationally expensive for LLMs; therefore, some studies have introduced alternative approaches, such as in-context learning (ICL)-based knowledge editing (IKE) which may not require any heavy parametric updates to LLMs [17,18]. Though IKE proves to be an effective and powerful method for LLMs to learn more context without requiring heavy parametric changes, it has limitations on how much additional information about an entity can be included.…”

Section: Introductionmentioning

confidence: 99%

Evaluating Complex Entity Knowledge Propagation for Knowledge Editing in LLMs

Shafqat,

2024

Applied Sciences

View full text Add to dashboard Cite

In today’s world, where information keeps growing rapidly and changing constantly, language models play a crucial role in making our lives easier across different fields. However, it is tough to keep these models updated with all the new data while making sure they stay accurate and relevant. To tackle this challenge, our study proposes an innovative approach to facilitate the propagation of complex entity knowledge within language models through extensive triplet representation. Using a specially curated dataset (CTR-KE) derived from reliable sources like Wikipedia and Wikidata, the research assesses the efficacy of editing methods in handling intricate relationships between entities across multiple tiers of information. By employing a comprehensive triplet representation strategy, the study aims to enrich contextual understanding while mitigating the risks associated with distorting or forgetting critical information. The study evaluates its proposed methodology using various evaluation metrics and four distinct editing methods across three diverse language models (GPT2-XL, GPT-J, and Llama-2-7b). The results indicate the superiority of mass-editing memory in a transformer (MEMIT) and in-context learning for knowledge editing (IKE) in efficiently executing multiple updates within the triplet representation framework. This research signifies a promising pathway for deeper exploration of data representation for knowledge editing within large language models, and improved understanding of contexts to facilitate continual learning.

show abstract

Section: Introductionmentioning

confidence: 99%

Evaluating Complex Entity Knowledge Propagation for Knowledge Editing in LLMs

Shafqat,

2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

Tenofovir versus entecavir for children and adults with chronic hepatitis B

Cited by 1 publication

References 50 publications

Evaluating Complex Entity Knowledge Propagation for Knowledge Editing in LLMs

Evaluating Complex Entity Knowledge Propagation for Knowledge Editing in LLMs

Contact Info

Product

Resources

About