Results 221 to 230 of about 51,786 (296)

Generating Compressed Counterfactual Hard Negative Samples for Graph Contrastive Learning

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Graph contrastive learning (GCL) relies on acquiring high‐quality positive and negative samples to learn the structural semantics of the input graph. Previous approaches typically sampled negative samples from the same training batch or an irrelevant external graph.
Haoran Yang, Hongxu Chen, Xiangyu Zhao, Sixiao Zhang, Xiangguo Sun, Qian Li, Hongzhi Yin, Guandong Xu   +7 more
wiley   +1 more source

Multitype Game Optimisation: A Two‐Stage Fine‐Tuning Framework for Multi‑Game Optimisation With Large Language Models

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Large language models (LLMs) have made remarkable advances in natural language processing, demonstrating great potential in modelling structured sequences. However, adapting these capabilities to machine gaming tasks such as Go remains challenging due to limitations in strategy generalisation and optimisation efficiency.
Xiali Li, Jingshi Gu, Feifan He, Yang Xiao, Yuanli Jia, Ping Lan   +5 more
wiley   +1 more source

From Ambiguous Queries to Verifiable Insights: A Task‐Driven Framework for LLM‐Powered SOC Analysis⋆

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Security operations centre (SOC) analysts must investigate alerts, correlate threat intelligence and interpret heterogeneous telemetry under tight timing constraints. Although large language models (LLMs) offer strong understanding capabilities, directly applying them to SOC environments remains challenging due to semantic ambiguity in analyst
Huan Zhang, Haiyan Wang, Hao Tan, Liyi Zeng, Jingnan Li, Zhaoquan Gu   +5 more
wiley   +1 more source

Natural language processing to enhance rheumatoid arthritis care in clinical studies: a scoping review of applications, data, approaches, challenges and future directions. [PDF]

Rheumatol Int
Huang Y, Agarwal SK.
europepmc   +1 more source

M3LoRA: Flexible Task Adaptation via Multiple Low‐Rank Matrices With Mixture‐of‐Subspaces and Minor Singular Components Initialization

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Parameter‐efficient fine‐tuning (PEFT) has become a crucial paradigm for domain adaptation, achieving strong performance by updating only a small fraction of model parameters. Among various PEFT methods, low‐rank adaptation (LoRA) is widely adopted due to its structural simplicity and computational efficiency.
Xu Luo, Yongbin Liu, Chunping Ouyang, Ying Yu, Yang Yang   +4 more
wiley   +1 more source

Optimizing merchant compliance: A system for product specific rule extraction using NLP. [PDF]

MethodsX
Khewalkar A, Walsepatil A, Phadtare R, Jadhav S, Shinde P, Chaudhari AY.   +5 more
europepmc   +1 more source

Multiple Transformer‐Based Models for Phase‐Sensitive Masking‐Based Single‐Channel Speech Enhancement

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Leveraging both global contextual dependencies and local temporal‐spectral patterns can further enhance speech quality and intelligibility, motivating the integration of diverse neural network structures for improved mask estimation. Furthermore, due to the limitations of existing time‐frequency phase‐aware masks, a new constrained phase ...
Matin Pashaian, Sanaz Seyedin
wiley   +1 more source

Trends in the use of adult-specific preference-weighted health-related quality of life instruments in clinical trials over the past 50 years: a protocol for a meta-research study using deep learning-based natural language processing and large language models. [PDF]

BMJ Open
Srikhom S, Devlin N, Nghiem N, Nolte S, Vo V, Tran-Duy A.   +5 more
europepmc   +1 more source

A Novel Full‐Chain Loop Tracking Auditing Framework for Obtaining Audit Evidence With Reasonable Assurance

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT As an attestation engagement, auditing is required to provide reasonable assurance for its conclusions. Traditional auditing has limited capacity to handle unstructured data and is usually based on audit sampling techniques, which can lead to the neglect of important audit evidence during the auditing process and result in a higher audit risk,
Xiaojia Wang, Ziqing Luo, Chaoxu Mu
wiley   +1 more source

A Technical Framework for Predicting Regulatory Deficiencies in Pharmaceutical Chemistry, Manufacturing, and Controls (CMC) Submissions Using Machine Learning. [PDF]

Cureus
Modi P.
europepmc   +1 more source