Haolin Jin

Pengyue Yang, Haolin Jin, Qingwen Zeng et al.

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 simultaneously created significant challenges in model discovery and adoption. Users struggle to navigate this landscape due to inconsistent, incomplete, and imbalanced documentation across platforms. Existing documentation frameworks, such as Model Cards and FactSheets, attempt to standardize reporting but are often static, predominantly qualitative, and lack the quantitative mechanisms needed for rigorous cross-model comparison. This gap exacerbates model underutilization and hinders responsible adoption. To address these shortcomings, we introduce the Comprehensive Responsible AI Model Card Framework (CRAI-MCF), a novel approach that transitions from static disclosures to actionable, human-aligned documentation. Grounded in Value Sensitive Design (VSD), CRAI-MCF is built upon an empirical analysis of 240 open-source projects, distilling 217 parameters into an eight-module, value-aligned architecture. Our framework introduces a quantitative sufficiency criterion to operationalize evaluation and enables rigorous cross-model comparison under a unified scheme. By balancing technical, ethical, and operational dimensions, CRAI-MCF empowers practitioners to efficiently assess, select, and adopt LLMs with greater confidence and operational integrity.

Zechao Sun, Shuying Piao, Haolin Jin et al.

Class Incremental Semantic Segmentation (CISS) aims to mitigate catastrophic forgetting by maintaining a balance between previously learned and newly introduced knowledge. Existing methods, primarily based on regularization techniques like knowledge distillation, help preserve old knowledge but often face challenges in effectively integrating new knowledge, resulting in limited overall improvement. Endpoints Weight Fusion (EWF) method, while simple, effectively addresses some of these limitations by dynamically fusing the model weights from previous steps with those from the current step, using a fusion parameter alpha determined by the relative number of previously known classes and newly introduced classes. However, the simplicity of the alpha calculation may limit its ability to fully capture the complexities of different task scenarios, potentially leading to suboptimal fusion outcomes. In this paper, we propose an enhanced approach called Adaptive Weight Fusion (AWF), which introduces an alternating training strategy for the fusion parameter, allowing for more flexible and adaptive weight integration. AWF achieves superior performance by better balancing the retention of old knowledge with the learning of new classes, significantly improving results on benchmark CISS tasks compared to the original EWF. And our experiment code will be released on Github.

Haolin Jin, Mengbai Xiao, Yuan Yuan et al.

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 series prediction. However, its core component, self-attention, has the quadratic time complexity relative to input sequence length, which hinders the scalability of Transformers. The exsiting approaches on optimizing self-attention either discard full-contextual information or lack of flexibility. In this work, we design DistrAttention, an effcient and flexible self-attention mechanism with the full context. DistrAttention achieves this by grouping data on the embedding dimensionality, usually referred to as $d$. We realize DistrAttention with a lightweight sampling and fusion method that exploits locality-sensitive hashing to group similar data. A block-wise grouping framework is further designed to limit the errors introduced by locality sensitive hashing. By optimizing the selection of block sizes, DistrAttention could be easily integrated with FlashAttention-2, gaining high-performance on modern GPUs. We evaluate DistrAttention with extensive experiments. The results show that our method is 37% faster than FlashAttention-2 on calculating self-attention. In ViT inference, DistrAttention is the fastest and the most accurate among approximate self-attention mechanisms. In Llama3-1B, DistrAttention still achieves the lowest inference time with only 1% accuray loss.

Lianwei Wu, Yuan Rao, Ambreen Nazir et al.

A series of deep learning approaches extract a large number of credibility features to detect fake news on the Internet. However, these extracted features still suffer from many irrelevant and noisy features that restrict severely the performance of the approaches. In this paper, we propose a novel model based on Adversarial Networks and inspirited by the Shared-Private model (ANSP), which aims at reducing common, irrelevant features from the extracted features for information credibility evaluation. Specifically, ANSP involves two tasks: one is to prevent the binary classification of true and false information for capturing common features relying on adversarial networks guided by reinforcement learning. Another extracts credibility features (henceforth, private features) from multiple types of credibility information and compares with the common features through two strategies, i.e., orthogonality constraints and KL-divergence for making the private features more differential. Experiments first on two six-label LIAR and Weibo datasets demonstrate that ANSP achieves the state-of-the-art performance, boosting the accuracy by 2.1%, 3.1%, respectively and then on four-label Twitter16 validate the robustness of the model with 1.8% performance improvements.

Lianwei Wu, Yuan Rao, Haolin Jin et al.

Recently, neural networks based on multi-task learning have achieved promising performance on fake news detection, which focus on learning shared features among tasks as complementary features to serve different tasks. However, in most of the existing approaches, the shared features are completely assigned to different tasks without selection, which may lead to some useless and even adverse features integrated into specific tasks. In this paper, we design a sifted multi-task learning method with a selected sharing layer for fake news detection. The selected sharing layer adopts gate mechanism and attention mechanism to filter and select shared feature flows between tasks. Experiments on two public and widely used competition datasets, i.e. RumourEval and PHEME, demonstrate that our proposed method achieves the state-of-the-art performance and boosts the F1-score by more than 0.87%, 1.31%, respectively.