Detecting AI-involved text is essential for combating misinformation, plagiarism, and academic misconduct. However, AI text generation includes diverse collaborative processes (AI-written text edited by humans, human-written text edited by AI, and AI-generated text refined by other AI), where various or even new LLMs could be involved. Texts generated through these varied processes exhibit complex characteristics, presenting significant challenges for detection. Current methods model these processes rather crudely, primarily employing binary classification (purely human vs. AI-involved) or multi-classification (treating human-AI collaboration as a new class). We observe that representations of texts generated through different processes exhibit inherent clustering relationships. Therefore, we propose DETree, a novel approach that models the relationships among different processes as a Hierarchical Affinity Tree structure, and introduces a specialized loss function that aligns text representations with this tree. To facilitate this learning, we developed RealBench, a comprehensive benchmark dataset that automatically incorporates a wide spectrum of hybrid texts produced through various human-AI collaboration processes. Our method improves performance in hybrid text detection tasks and significantly enhances robustness and generalization in out-of-distribution scenarios, particularly in few-shot learning conditions, further demonstrating the promise of training-based approaches in OOD settings. Our code and dataset are available at https://github.com/heyongxin233/DETree.

Current techniques for detecting AI-generated text are largely confined to manual feature crafting and supervised binary classification paradigms. These methodologies typically lead to performance bottlenecks and unsatisfactory generalizability. Consequently, these methods are often inapplicable for out-of-distribution (OOD) data and newly emerged large language models (LLMs). In this paper, we revisit the task of AI-generated text detection. We argue that the key to accomplishing this task lies in distinguishing writing styles of different authors, rather than simply classifying the text into human-written or AI-generated text. To this end, we propose DeTeCtive, a multi-task auxiliary, multi-level contrastive learning framework. DeTeCtive is designed to facilitate the learning of distinct writing styles, combined with a dense information retrieval pipeline for AI-generated text detection. Our method is compatible with a range of text encoders. Extensive experiments demonstrate that our method enhances the ability of various text encoders in detecting AI-generated text across multiple benchmarks and achieves state-of-the-art results. Notably, in OOD zero-shot evaluation, our method outperforms existing approaches by a large margin. Moreover, we find our method boasts a Training-Free Incremental Adaptation (TFIA) capability towards OOD data, further enhancing its efficacy in OOD detection scenarios. We will open-source our code and models in hopes that our work will spark new thoughts in the field of AI-generated text detection, ensuring safe application of LLMs and enhancing compliance.

Gene regulatory network plays a crucial role in controlling the biological processes of living creatures. Deciphering the complex gene regulatory networks from experimental data remains a major challenge in system biology. Recent advances in single-cell RNA sequencing technology bring massive high-resolution data, enabling computational inference of cell-specific gene regulatory networks (GRNs). Many relevant algorithms have been developed to achieve this goal in the past years. However, GRN inference is still less ideal due to the extra noises involved in pseudo-time information and large amounts of dropouts in datasets. Here, we present a novel GRN inference method named Normi, which is based on non-redundant mutual information. Normi manipulates these problems by employing a sliding size-fixed window approach on the entire trajectory and conducts average smoothing strategy on the gene expression of the cells in each window to obtain representative cells. To further alleviate the impact of dropouts, we utilize the mixed KSG estimator to quantify the high-order time-delayed mutual information among genes, then filter out the redundant edges by adopting Max-Relevance and Min Redundancy algorithm. Moreover, we determined the optimal time delay for each gene pair by distance correlation. Normi outperforms other state-of-the-art GRN inference methods on both simulated data and single-cell RNA sequencing (scRNA-seq) datasets, demonstrating its superiority in robustness. The performance of Normi in real scRNA-seq data further reveals its ability to identify the key regulators and crucial biological processes.