Zhi Li

Fulin Gao, Weimin Zhong, Zhixing Cao et al.

A desirable open world recognition (OWR) system requires performing three tasks: (1) Open set recognition (OSR), i.e., classifying the known (classes seen during training) and rejecting the unknown (unseen$/$novel classes) online; (2) Grouping and labeling these unknown as novel known classes; (3) Incremental learning (IL), i.e., continual learning these novel classes and retaining the memory of old classes. Ideally, all of these steps should be automated. However, existing methods mostly assume that the second task is completely done manually. To bridge this gap, we propose OpenGCD that combines three key ideas to solve the above problems sequentially: (a) We score the origin of instances (unknown or specifically known) based on the uncertainty of the classifier's prediction; (b) For the first time, we introduce generalized category discovery (GCD) techniques in OWR to assist humans in grouping unlabeled data; (c) For the smooth execution of IL and GCD, we retain an equal number of informative exemplars for each class with diversity as the goal. Moreover, we present a new performance evaluation metric for GCD called harmonic clustering accuracy. Experiments on two standard classification benchmarks and a challenging dataset demonstrate that OpenGCD not only offers excellent compatibility but also substantially outperforms other baselines. Code: https://github.com/Fulin-Gao/OpenGCD.

Taiji Li, Zhi Li, Yin Zhang

Despite large language models (LLMs) have demonstrated impressive performance in various tasks, they are still suffering from the factual inconsistency problem called hallucinations. For instance, LLMs occasionally generate content that diverges from source article, and prefer to extract information that appears at the beginning and end of the context, especially in long document summarization. Inspired by these findings, we propose to improve the faithfulness of LLMs in summarization by impelling them to process the entire article more fairly and faithfully. We present a novel summary generation strategy, namely SliSum, which exploits the ideas of sliding windows and self-consistency. Specifically, SliSum divides the source article into overlapping windows, and utilizes LLM to generate local summaries for the content in the windows. Finally, SliSum aggregates all local summaries using clustering and majority voting algorithm to produce more faithful summary of entire article. Extensive experiments demonstrate that SliSum significantly improves the faithfulness of diverse LLMs including LLaMA-2, Claude-2 and GPT-3.5 in both short and long text summarization, while maintaining their fluency and informativeness and without additional fine-tuning and resources. We further conduct qualitative and quantitative studies to investigate why SliSum works and impacts of hyperparameters in SliSum on performance.

Sihai Guan, Zhi Li

The learning speed of an adaptive algorithm can be improved by properly constraining the cost function of the adaptive algorithm. Besides, the stabilization of the NCLMF algorithm is more complicated, whose stability depends solely on the input power of the adaptive filter and the NCLMF algorithm with unbounded repressors is not mean square stability even for a small value of the step-size. So, in this paper, a noise variance constrained least mean absolute third (LMAT) algorithm is investigated. The noise constrained LMAT (NCLMAT) algorithm is obtained by constraining the cost function of the standard LMAT algorithm to the third-order moment of the additive noise. And it can eliminate a variety of non-Gaussian distribution of noise, such as Rayleigh noise, Binary noise and so on. The NCLMAT algorithm is a type of variable step-size LMAT algorithm where the step-size rule arises naturally from the constraints. The main aim of this work is first time to derive the NCLMAT adaptive algorithm, analyze its convergence behavior, mean square error (MSE), mean-square deviation (MSD) and assess its performance in different noise environments. Finally, the experimental results in system identification applications presented here illustrate the principle and efficiency of the NCLMAT algorithm.