10 papers
Human-aligned AI Model Cards with Weighted Hierarchy Architecture
Pengyue Yang, Haolin Jin, Qingwen Zeng +3
The proliferation of Large Language Models (LLMs) has led to a burgeoning ecosystem of specialized, domain-specific models. While this rapid growth accelerates innovation, it has s…
Are LLMs Reliable Code Reviewers? Systematic Overcorrection in Requirement Conformance Judgement
Haolin Jin, Huaming Chen
Large language models (LLMs) have become essential tools in software development, widely used for requirements engineering, code generation and review tasks. Software engineers oft…
Trust in One Round: Confidence Estimation for Large Language Models via Structural Signals
Pengyue Yang, Jiawen Wen, Haolin Jin +3
Large language models (LLMs) are increasingly deployed in domains where errors carry high social, scientific, or safety costs. Yet standard confidence estimators, such as token lik…
Uncovering Systematic Failures of LLMs in Verifying Code Against Natural Language Specifications
Haolin Jin, Huaming Chen
Large language models (LLMs) have become essential tools in software development, widely used for requirements engineering, code generation and review tasks. Software engineers oft…
DistrAttention: An Efficient and Flexible Self-Attention Mechanism on Modern GPUs
Haolin Jin, Mengbai Xiao, Yuan Yuan +4
The Transformer architecture has revolutionized deep learning, delivering the state-of-the-art performance in areas such as natural language processing, computer vision, and time s…
AWF: Adaptive Weight Fusion for Enhanced Class Incremental Semantic Segmentation
Zechao Sun, Shuying Piao, Haolin Jin +4
Class Incremental Semantic Segmentation (CISS) aims to mitigate catastrophic forgetting by maintaining a balance between previously learned and newly introduced knowledge. Existing…