Liang Wang

Mengqi Zhang, Bowen Fang, Qiang Liu et al.

Large language models (LLMs) face challenges with internal knowledge inaccuracies and outdated information. Knowledge editing has emerged as a pivotal approach to mitigate these issues. Although current knowledge editing techniques exhibit promising performance in single-hop reasoning tasks, they show limitations when applied to multi-hop reasoning. Drawing on cognitive neuroscience and the operational mechanisms of LLMs, we hypothesize that the residual single-hop knowledge after editing causes edited models to revert to their original answers when processing multi-hop questions, thereby undermining their performance in multihop reasoning tasks. To validate this hypothesis, we conduct a series of experiments that empirically confirm our assumptions. Building on the validated hypothesis, we propose a novel knowledge editing method that incorporates a Knowledge Erasure mechanism for Large language model Editing (KELE). Specifically, we design an erasure function for residual knowledge and an injection function for new knowledge. Through joint optimization, we derive the optimal recall vector, which is subsequently utilized within a rank-one editing framework to update the parameters of targeted model layers. Extensive experiments on GPT-J and GPT-2 XL demonstrate that KELE substantially enhances the multi-hop reasoning capability of edited LLMs.

Yilan Qin, Jiayu Ma, Mingle Jiang et al.

Kinetic approaches are generally accurate in dealing with microscale plasma physics problems but are computationally expensive for large-scale or multiscale systems. One of the long-standing problems in plasma physics is the integration of kinetic physics into fluid models, which is often achieved through sophisticated analytical closure terms. In this paper, we successfully construct a multi-moment fluid model with an implicit fluid closure included in the neural network using machine learning. The multi-moment fluid model is trained with a small fraction of sparsely sampled data from kinetic simulations of Landau damping, using the physics-informed neural network (PINN) and the gradient-enhanced physics-informed neural network (gPINN). The multi-moment fluid model constructed using either PINN or gPINN reproduces the time evolution of the electric field energy, including its damping rate, and the plasma dynamics from the kinetic simulations. In addition, we introduce a variant of the gPINN architecture, namely, gPINN$p$ to capture the Landau damping process. Instead of including the gradients of all the equation residuals, gPINN$p$ only adds the gradient of the pressure equation residual as one additional constraint. Among the three approaches, the gPINN$p$-constructed multi-moment fluid model offers the most accurate results. This work sheds light on the accurate and efficient modeling of large-scale systems, which can be extended to complex multiscale laboratory, space, and astrophysical plasma physics problems.

Yu Wang, Nan Yang, Liang Wang et al.

Recent advancements in language models have led to significant improvements in mathematical reasoning across various benchmarks. However, most of these benchmarks rely on automatic evaluation methods that only compare final answers using heuristics, without verifying the underlying reasoning steps. This limitation results in false positive solutions, where models may produce correct final answers but with flawed deduction paths. In this paper, we systematically examine the prevalence of false positive solutions in mathematical problem solving for language models. We analyze the characteristics and extent of this issue across different open-source models, datasets of varying difficulty levels, and decoding strategies. Specifically, we explore how false positives influence the inference time scaling behavior of language models. Our experimental results reveal that: (1) false positive solutions persist across different models, datasets, and decoding methods, (2) sampling-based inference time scaling methods do not alleviate the problem, and (3) the pass@N evaluation metric is more susceptible to false positives, suggesting a significantly lower scaling ceiling than what automatic evaluations indicate. Additionally, we analyze specific instances of false positives and discuss potential limitations in self-improvement techniques and synthetic data generation under such conditions. Our data and code are publicly available at https://github.com/Wloner0809/False-Positives-in-Math.

Mengqi Zhang, Yanqiao Zhu, Qiang Liu et al.

Multiview network embedding aims at projecting nodes in the network to low-dimensional vectors, while preserving their multiple relations and attribute information. Contrastive learning approaches have shown promising performance in this task. However, they neglect the semantic consistency between fused and view representations and have difficulty in modeling complementary information between different views. To deal with these deficiencies, this work presents a novel Contrastive leaRning framEwork for Multiview network Embedding (CREME). In our work, different views can be obtained based on the various relations among nodes. Then, we generate view embeddings via proper view encoders and utilize an attentive multiview aggregator to fuse these representations. Particularly, we design two collaborative contrastive objectives, view fusion InfoMax and inter-view InfoMin, to train the model in a self-supervised manner. The former objective distills information from embeddings generated from different views, while the latter captures complementary information among views to promote distinctive view embeddings. We also show that the two objectives can be unified into one objective for model training. Extensive experiments on three real-world datasets demonstrate that our proposed CREME is able to consistently outperform state-of-the-art methods.

Zekun Li, Yujia Zheng, Shu Wu et al.

Graph-based collaborative filtering (CF) algorithms have gained increasing attention. Existing work in this literature usually models the user-item interactions as a bipartite graph, where users and items are two isolated node sets and edges between them indicate their interactions. Then, the unobserved preference of users can be exploited by modeling high-order connectivity on the bipartite graph. In this work, we propose to model user-item interactions as a heterogeneous graph which consists of not only user-item edges indicating their interaction but also user-user edges indicating their similarity. We develop heterogeneous graph collaborative filtering (HGCF), a GCN-based framework which can explicitly capture both the interaction signal and similarity signal through embedding propagation on the heterogeneous graph. Since the heterogeneous graph is more connected than the bipartite graph, the sparsity issue can be alleviated and the demand for expensive high-order connectivity modeling can be lowered. Extensive experiments conducted on three public benchmarks demonstrate its superiority over the state-of-the-arts. Further analysis verifies the importance of user-user edges in the graph, justifying the rationality and effectiveness of HGCF.