Large Language Models (LLMs) have achieved remarkable success in natural language tasks, yet understanding their reasoning processes remains a significant challenge.We address this by introducing XplainLLM, a dataset accompanying an explanation framework designed to enhance LLM transparency and reliability.Our dataset comprises 24,204 instances where each instance interprets the LLM's reasoning behavior using knowledge graphs (KGs) and graph attention networks (GAT), and includes explanations of LLMs such as the decoderonly Llama-3 and the encoder-only RoBERTa.XplainLLM also features a framework for generating grounded explanations and the debuggerscores for multidimensional quality analysis.Our explanations include why-choose and whynot-choose components, reason-elements, and debugger-scores that collectively illuminate the LLM's reasoning behavior.Our evaluations demonstrate XplainLLM's potential to reduce hallucinations and improve grounded explanation generation in LLMs.XplainLLM is a resource for researchers and practitioners to build trust and verify the reliability of LLM outputs.Our code and dataset are publicly available 1 .

In reinforcement learning with image-based inputs, it is crucial to establish a robust and generalizable state representation. Recent advancements in metric learning, such as deep bisimulation metric approaches, have shown promising results in learning structured low-dimensional representation space from pixel observations, where the distance between states is measured based on task-relevant features. However, these approaches face challenges in demanding generalization tasks and scenarios with non-informative rewards. This is because they fail to capture sufficient long-term information in the learned representations. To address these challenges, we propose a novel State Chrono Representation (SCR) approach. SCR augments state metric-based representations by incorporating extensive temporal information into the update step of bisimulation metric learning. It learns state distances within a temporal framework that considers both future dynamics and cumulative rewards over current and long-term future states. Our learning strategy effectively incorporates future behavioral information into the representation space without introducing a significant number of additional parameters for modeling dynamics. Extensive experiments conducted in DeepMind Control and Meta-World environments demonstrate that SCR achieves better performance comparing to other recent metric-based methods in demanding generalization tasks. The codes of SCR are available in https://github.com/jianda-chen/SCR.

Artificial intelligence (AI)-empowered industrial fault diagnostics is important in ensuring the safe operation of industrial applications. Since complex industrial systems often involve multiple industrial plants (possibly belonging to different companies or subsidiaries) with sensitive data collected and stored in a distributed manner, collaborative fault diagnostic model training often needs to leverage federated learning (FL). As the scale of the industrial fault diagnostic models are often large and communication channels in such systems are often not exclusively used for FL model training, existing deployed FL model training frameworks cannot train such models efficiently across multiple institutions. In this paper, we report our experience developing and deploying the Federated Opportunistic Block Dropout (FedOBD) approach for industrial fault diagnostic model training. By decomposing large-scale models into semantic blocks and enabling FL participants to opportunistically upload selected important blocks in a quantized manner, it significantly reduces the communication overhead while maintaining model performance. Since its deployment in ENN Group in February 2022, FedOBD has served two coal chemical plants across two cities in China to build industrial fault prediction models. It helped the company reduce the training communication overhead by over 70% compared to its previous AI Engine, while maintaining model performance at over 85% test F1 score. To our knowledge, it is the first successfully deployed dropout-based FL approach.

Large-scale neural networks possess considerable expressive power. They are well-suited for complex learning tasks in industrial applications. However, large-scale models pose significant challenges for training under the current Federated Learning (FL) paradigm. Existing approaches for efficient FL training often leverage model parameter dropout. However, manipulating individual model parameters is not only inefficient in meaningfully reducing the communication overhead when training large-scale FL models, but may also be detrimental to the scaling efforts and model performance as shown by recent research. To address these issues, we propose the Federated Opportunistic Block Dropout (FedOBD) approach. The key novelty is that it decomposes large-scale models into semantic blocks so that FL participants can opportunistically upload quantized blocks, which are deemed to be significant towards training the model, to the FL server for aggregation. Extensive experiments evaluating FedOBD against four state-of-the-art approaches based on multiple real-world datasets show that it reduces the overall communication overhead by more than 88% compared to the best performing baseline approach, while achieving the highest test accuracy. To the best of our knowledge, FedOBD is the first approach to perform dropout on FL models at the block level rather than at the individual parameter level.

Federated Learning (FL) enables participants to "share'' their sensitive local data in a privacy preserving manner and collaboratively build machine learning models. In order to sustain long-term participation by high quality data owners (especially if they are businesses), FL systems need to provide suitable incentives. To design an effective incentive scheme, it is important to understand how FL participants respond under such schemes. This paper proposes FedGame, a multi-player game to study how FL participants make action selection decisions under different incentive schemes. It allows human players to role-play under various conditions. The decision-making processes can be analyzed and visualized to inform FL incentive mechanism design in the future.

A planar capacitive sensor (PCS) capable of 2D large-scale measurement is presented in this paper. Displacement interpretation depends on independently measuring the periodic variation in capacitance caused by the change in the overlapping area of sensing electrodes on a moving plate and a fixed plate. By accumulating the number of quarters in each direction and the specific position in the final quarter, the large-scale measurement is fulfilled. Displacements in X - and Y -direction can be measured independently and simultaneously. Simulation shows that a shorter gap distance and a longer electrode guarantee better sensitivity. Experiments based on a PCS test bench demonstrate that the PCS has a sensitivity of 0.198 mV/μm and a resolution of 0.308 μm. An electric fringe effect and other possible measurement errors on displacement interpretation accuracy are discussed. The study confirms the high potential of PCSs as innovative 2D long-range displacement sensors.

Based on the system of thermal-vibration combined test environment under high-linear acceleration, profound study on the distribution and control of the temperature field of the temperature box in a centrifugal field has been carried out in this paper. Firstly, a finite element model of the temperature box in the centrifugal field has been set up to reveal the mechanism of how centrifugal field influences temperature field. Secondly, taking the finite element model of temperature box in the centrifugal field as a controlled object and adopting the method of fuzzy control, simulation study on temperature control in the temperature box has been done. Finally, parts of the results are validated with experiment, and some measures are put forwards, which could ameliorate performance index such as temperature-rising speed, fluctuation ratio and temperature evenness in the temperature box.