Sizhe Zhang

Guiyao Tie, Zenghui Yuan, Zeli Zhao et al.

Self-correction of large language models (LLMs) emerges as a critical component for enhancing their reasoning performance. Although various self-correction methods have been proposed, a comprehensive evaluation of these methods remains largely unexplored, and the question of whether LLMs can truly correct themselves is a matter of significant interest and concern. In this study, we introduce CorrectBench, a benchmark developed to evaluate the effectiveness of self-correction strategies, including intrinsic, external, and fine-tuned approaches, across three tasks: commonsense reasoning, mathematical reasoning, and code generation. Our findings reveal that: 1) Self-correction methods can improve accuracy, especially for complex reasoning tasks; 2) Mixing different self-correction strategies yields further improvements, though it reduces efficiency; 3) Reasoning LLMs (e.g., DeepSeek-R1) have limited optimization under additional self-correction methods and have high time costs. Interestingly, a comparatively simple chain-of-thought (CoT) baseline demonstrates competitive accuracy and efficiency. These results underscore the potential of self-correction to enhance LLM's reasoning performance while highlighting the ongoing challenge of improving their efficiency. Consequently, we advocate for further research focused on optimizing the balance between reasoning capabilities and operational efficiency. Project Page: https://correctbench.github.io/

Junhuan Yang, Yi Sheng, Sizhe Zhang et al.

This paper represents the first effort to explore an automated architecture search for hyperdimensional computing (HDC), a type of brain-inspired neural network. Currently, HDC design is largely carried out in an application-specific ad-hoc manner, which significantly limits its application. Furthermore, the approach leads to inferior accuracy and efficiency, which suggests that HDC cannot perform competitively against deep neural networks. Herein, we present a thorough study to formulate an HDC architecture search space. On top of the search space, we apply reinforcement-learning to automatically explore the HDC architectures. The searched HDC architectures show competitive performance on case studies involving a drug discovery dataset and a language recognition task. On the Clintox dataset, which tries to learn features from developed drugs that passed/failed clinical trials for toxicity reasons, the searched HDC architecture obtains the state-of-the-art ROC-AUC scores, which are 0.80% higher than the manually designed HDC and 9.75% higher than conventional neural networks. Similar results are achieved on the language recognition task, with 1.27% higher performance than conventional methods.

Jinghao Wen, Dongning Ma, Sizhe Zhang et al.

Hyperdimensional Computing (HDC) is a promising bio-inspired learning paradigm for its advantage of balancing performance and efficiency and has been increasingly applied to the bio-medical domain. In bio-medical applications, trustworthiness such as replicability and verifiability of the trained learning models is crucial. In this work, we introduce HDCoin, the first proof-of-useful-work blockchain framework for HDC. With HDCoin, we transform the conventional energy-wasteful mining process into a competitive process for developing high accuracy, trustworthy and verifiable hyperdimensional models. We explore four diverse biomedical datasets, and conduct an extensive design-space exploration of key HDC hyperparameters of blockchain miners such as dimensionality, learning rate, and retraining iterations for model performance, adaptive mining difficulty and fairness on proof-of-useful-work.