Zobrazeno 1 - 10
of 577
pro vyhledávání: '"Su, Sen"'
Mixture-of-Experts (MoE) shines brightly in large language models (LLMs) and demonstrates outstanding performance in plentiful natural language processing tasks. However, existing methods transforming LLMs from dense to MoE face significant data requ
Externí odkaz:
http://arxiv.org/abs/2410.01610
The study of oracle characters plays an important role in Chinese archaeology and philology. However, the difficulty of collecting and annotating real-world scanned oracle characters hinders the development of oracle character recognition. In this pa
Externí odkaz:
http://arxiv.org/abs/2409.15893
Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability Distributions
Large language models are susceptible to jailbreak attacks, which can result in the generation of harmful content. While prior defenses mitigate these risks by perturbing or inspecting inputs, they ignore competing objectives, the underlying cause of
Externí odkaz:
http://arxiv.org/abs/2408.07663
Large Language Models (LLMs) have been demonstrated to generate illegal or unethical responses, particularly when subjected to "jailbreak." Research on jailbreak has highlighted the safety issues of LLMs. However, prior studies have predominantly foc
Externí odkaz:
http://arxiv.org/abs/2402.17262
Deep neural networks (DNNs) are often prone to learn the spurious correlations between target classes and bias attributes, like gender and race, inherent in a major portion of training data (bias-aligned samples), thus showing unfair behavior and ari
Externí odkaz:
http://arxiv.org/abs/2401.02150
Ancient history relies on the study of ancient characters. However, real-world scanned oracle characters are difficult to collect and annotate, posing a major obstacle for oracle character recognition (OrCR). Besides, serious abrasion and inter-class
Externí odkaz:
http://arxiv.org/abs/2312.06075
Relation triple extraction (RTE) is an essential task in information extraction and knowledge graph construction. Despite recent advancements, existing methods still exhibit certain limitations. They just employ generalized pre-trained models and do
Externí odkaz:
http://arxiv.org/abs/2309.11853
Large language models (LLMs) have been proven capable of memorizing their training data, which can be extracted through specifically designed prompts. As the scale of datasets continues to grow, privacy risks arising from memorization have attracted
Externí odkaz:
http://arxiv.org/abs/2308.15727
Social network alignment shows fundamental importance in a wide spectrum of applications. To the best of our knowledge, existing studies mainly focus on network alignment at the individual user level, requiring abundant common information between sha
Externí odkaz:
http://arxiv.org/abs/2209.02908
