Generative commonsense reasoning (GCR) in natural language is to reason about the commonsense while generating coherent text.Recent years have seen a surge of interest in improving the generation quality of commonsense reasoning tasks.Nevertheless, these approaches have seldom investigated diversity in the GCR tasks, which aims to generate alternative explanations for a real-world situation or predict all possible outcomes.Diversifying GCR is challenging as it expects to generate multiple outputs that are not only semantically different but also grounded in commonsense knowledge.In this paper, we propose MoKGE, a novel method that diversifies the generative reasoning by a mixture of expert (MoE) strategy on commonsense knowledge graphs (KG).A set of knowledge experts seek diverse reasoning on KG to encourage various generation outputs.Empirical experiments demonstrated that MoKGE can significantly improve the diversity while achieving on par performance on accuracy on two GCR benchmarks, based on both automatic and human evaluations.
Recommendation systems for Web content distribution intricately connect to the information access and exposure opportunities for vulnerable populations. The emergence of Large Language Models-based Recommendation System (LRS) may introduce additional societal challenges to recommendation systems due to the inherent biases in Large Language Models (LLMs). From the perspective of item-side fairness, there remains a lack of comprehensive investigation into the item-side fairness of LRS given the unique characteristics of LRS compared to conventional recommendation systems. To bridge this gap, this study examines the property of LRS with respect to item-side fairness and reveals the influencing factors of both historical users' interactions and inherent semantic biases of LLMs, shedding light on the need to extend conventional item-side fairness methods for LRS. Towards this goal, we develop a concise and effective framework called IFairLRS to enhance the item-side fairness of an LRS. IFairLRS covers the main stages of building an LRS with specifically adapted strategies to calibrate the recommendations of LRS. We utilize IFairLRS to fine-tune LLaMA, a representative LLM, on \textit{MovieLens} and \textit{Steam} datasets, and observe significant item-side fairness improvements. The code can be found in https://github.com/JiangM-C/IFairLRS.git.
Purpose The purpose of this paper is to study the reliability of sintered nano-silver joints on bare copper substrates during high-temperature storage (HTS). Design/methodology/approach In this study, HTS at 250 °C was carried out to investigate the reliability of nano-silver sintered joints. Combining the evolution of the microstructure and shear strength of the joints, the degradation mechanisms of joints performance were characterized. Findings The results indicated that the degradation of the shear properties of sintered nano-silver joints on copper substrates was attributed to copper oxidation at the silver/copper interface and interdiffusion of interfacial elements. The joints decreased by approximately 57.4% compared to the original joints after aging for 500 h. In addition, severe coarsening of the silver structure was also an important cause for joints failure during HTS. Originality/value This paper provides a comparison of quantitative and mechanistic evaluation of sintered silver joints on bare copper substrates during HTS, which is of great importance in promoting the development of sintered silver technology.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)