Du Wei

Tianjie Ju, Yijin Chen, Xinwei Yuan et al.

Recent work has showcased the powerful capability of large language models (LLMs) in recalling knowledge and reasoning. However, the reliability of LLMs in combining these two capabilities into reasoning through multi-hop facts has not been widely explored. This paper systematically investigates the possibilities for LLMs to utilize shortcuts based on direct connections between the initial and terminal entities of multi-hop knowledge. We first explore the existence of factual shortcuts through Knowledge Neurons, revealing that: (i) the strength of factual shortcuts is highly correlated with the frequency of co-occurrence of initial and terminal entities in the pre-training corpora; (ii) few-shot prompting leverage more shortcuts in answering multi-hop questions compared to chain-of-thought prompting. Then, we analyze the risks posed by factual shortcuts from the perspective of multi-hop knowledge editing. Analysis shows that approximately 20% of the failures are attributed to shortcuts, and the initial and terminal entities in these failure instances usually have higher co-occurrences in the pre-training corpus. Finally, we propose erasing shortcut neurons to mitigate the associated risks and find that this approach significantly reduces failures in multiple-hop knowledge editing caused by shortcuts.

Wenxuan Fang, Wei Du, Renchu He et al.

Gasoline blending scheduling uses resource allocation and operation sequencing to meet a refinery's production requirements. The presence of nonlinearity, integer constraints, and a large number of decision variables adds complexity to this problem, posing challenges for traditional and evolutionary algorithms. This paper introduces a novel multiobjective optimization approach driven by a diffusion model (named DMO), which is designed specifically for gasoline blending scheduling. To address integer constraints and generate feasible schedules, the diffusion model creates multiple intermediate distributions between Gaussian noise and the feasible domain. Through iterative processes, the solutions transition from Gaussian noise to feasible schedules while optimizing the objectives using the gradient descent method. DMO achieves simultaneous objective optimization and constraint adherence. Comparative tests are conducted to evaluate DMO's performance across various scales. The experimental results demonstrate that DMO surpasses state-of-the-art multiobjective evolutionary algorithms in terms of efficiency when solving gasoline blending scheduling problems.

Yubin Xiao, Di Wang, Xuan Wu et al.

Neural models produce promising results when solving Vehicle Routing Problems (VRPs), but often fall short in generalization. Recent attempts to enhance model generalization often incur unnecessarily large training cost or cannot be directly applied to other models solving different VRP variants. To address these issues, we take a novel perspective on model architecture in this study. Specifically, we propose a plug-and-play Entropy-based Scaling Factor (ESF) and a Distribution-Specific (DS) decoder to enhance the size and distribution generalization, respectively. ESF adjusts the attention weight pattern of the model towards familiar ones discovered during training when solving VRPs of varying sizes. The DS decoder explicitly models VRPs of multiple training distribution patterns through multiple auxiliary light decoders, expanding the model representation space to encompass a broader range of distributional scenarios. We conduct extensive experiments on both synthetic and widely recognized real-world benchmarking datasets and compare the performance with seven baseline models. The results demonstrate the effectiveness of using ESF and DS decoder to obtain a more generalizable model and showcase their applicability to solve different VRP variants, i.e., travelling salesman problem and capacitated VRP. Notably, our proposed generic components require minimal computational resources, and can be effortlessly integrated into conventional generalization strategies to further elevate model generalization.