Xintao Wang, Jian Yang, Weiyuan Li, Rui Xie, Jen-tse Huang, Jun Gao, Shuai Huang, Yueping Kang, Yuanli Guo, Hongwei Feng, Yanghua Xiao. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Zhouhong Gu, Xingzhou Chen, Xiaoran Shi, Tao Wang, Suhang Zheng, Tianyu Li, Hongwei Feng, Yanghua Xiao. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

The effective utilization of structured data, integral to corporate data strategies, has been challenged by the rise of large language models (LLMs) capable of processing unstructured information.This shift prompts the question: can LLMs interpret structured data directly in its unstructured form?We propose an automatic evaluation data generation method for assessing LLMs' reasoning capabilities on structurerich text to explore this.Our approach supports 8 structured languages and 29 tasks, generating data with adjustable complexity through controllable nesting and structural width.We introduce StrucText-Eval, a benchmark containing 5,800 pre-generated and annotated samples designed to evaluate how well LLMs understand and reason through structured text.StrucText-Eval is divided into two suites: a regular Test suite (3,712 samples) and a Test-Hard suite (2,088 samples), the latter emphasizing the gap between human and model performance on more complex tasks.Experimental results show that while open-source LLMs achieve a maximum accuracy of 74.9% on the standard dataset, their performance drops significantly to 45.8% on the harder dataset.In contrast, human participants reach an accuracy of 92.6% on StrucText-Eval-Hard, highlighting LLMs' current limitations in handling intricate structural information.The benchmark and generation codes are open sourced in https://github.com/MikeGu721/ StrucText-Eval

Explainable fake news detection predicts the authenticity of news items with annotated explanations. Today, Large Language Models (LLMs) are known for their powerful natural language understanding and explanation generation abilities. However, using LLMs for explainable fake news detection remains two main challenges. Firstly, fake news appears reasonable and could easily mislead LLMs, leaving them unable to understand the complex news-faking process. Secondly, utilizing LLMs for this task would generate correct and incorrect explanations, requiring abundant labor in the loop. In this paper, we propose LLM-GAN, a novel framework that utilizes prompting mechanisms to enable an LLM to function as a Generator and a Detector for realistic fake news generation and detection. Extensive experimental results demonstrate LLM-GAN’s effectiveness in both prediction performance and explanation quality.

Large Language Models have revolutionized numerous tasks with their remarkable efficacy. However, editing these models, crucial for rectifying outdated or erroneous information, often leads to a complex issue known as the ripple effect in the hidden space. While difficult to detect, this effect can significantly impede the efficacy of model editing tasks and deteriorate model performance. This paper addresses this scientific challenge by proposing a novel evaluation methodology, Graphical Impact Evaluation(GIE), which quantitatively evaluates the adaptations of the model and the subsequent impact of editing. Furthermore, we introduce the Selective Impact Revision(SIR), a model editing method designed to mitigate this ripple effect. Our comprehensive evaluations reveal that the ripple effect in the hidden space is a significant issue in all current model editing methods. However, our proposed methods, GIE and SIR, effectively identify and alleviate this issue, contributing to the advancement of LLM editing techniques.

New Natural Langauge Process~(NLP) benchmarks are urgently needed to align with the rapid development of large language models (LLMs). We present Xiezhi, the most comprehensive evaluation suite designed to assess holistic domain knowledge.Xiezhi comprises multiple-choice questions across 516 diverse disciplines ranging from 13 different subjects with 249,587 questions and accompanied by Xiezhi-Specialty with 14,041 questions and Xiezhi-Interdiscipline with 10,746 questions. We conduct evaluation of the 47 cutting-edge LLMs on Xiezhi. Results indicate that LLMs exceed average performance of humans in science, engineering, agronomy, medicine, and art, but fall short in economics, jurisprudence, pedagogy, literature, history, and management. All the evaluation code and data are open sourced in https://github.com/MikeGu721/XiezhiBenchmark

Taxonomy is formulated as directed acyclic graphs or trees of concepts that support many downstream tasks. Many new coming concepts need to be added to an existing taxonomy. The traditional taxonomy expansion task aims only at finding the best position for new coming concepts in the existing taxonomy. However, they have two drawbacks when being applied to the real-scenarios. The previous methods suffer from low-efficiency since they waste much time when most of the new coming concepts are indeed noisy concepts. They also suffer from low-effectiveness since they collect training samples only from the existing taxonomy, which limits the ability of the model to mine more hypernym-hyponym relationships among real concepts. This paper proposes a pluggable framework called Generative Adversarial Network for Taxonomy Entering Evaluation (GANTEE) to alleviate these drawbacks. A generative adversarial network is designed in this framework by discriminative models to alleviate the first drawback and the generative model to alleviate the second drawback. Two discriminators are used in GANTEE to provide long-term and short-term rewards, respectively. Moreover, to further improve the efficiency, pre-trained language models are used to retrieve the representation of the concepts quickly. The experiments on three real-world large-scale datasets with two different languages show that GANTEE improves the performance of the existing taxonomy expansion methods in both effectiveness and efficiency.

In wireless power transfer (WPT) systems, inverters are used to achieve high‐frequency conversion of DC/AC, and their conversion efficiency and working frequency are key factors affecting the system’s power transfer efficiency. In practical applications, many hardware issues, such as power transistor shutdown and loss, are the main reasons that affect the inverter conversion efficiency. On the other hand, the working frequency of WPT systems ranges from hundreds of kHz to a few MHz, and traditional voltage and current phasor estimation requires a very high sampling rate which is difficult to achieve. To overcome these limitations, this paper introduces a phase‐shifting full bridge inverter using a zero‐voltage switching (ZVS) soft switching technology to optimize the conversion efficiency of the inverter. Meanwhile, apparent power is introduced to detect the operating frequency and phase angle. Combined with an FPGA soft switching control strategy, this approach allows for the quick adjustment of the driving pulse of MOS transistors, as well as the voltage and current at the transmitting end, to a completely symmetrical state in real‐time, effectively suppressing frequency offset and achieving efficient frequency tracking control and maximum efficiency tracking (MET) control of the WPT system. Through simulation and experiments, the ZVS soft switching technology has been achieved with the inverter control strategy, leading to improved conversion efficiency. The frequency offset that can be corrected can reach 0.1 Hz using the apparent power detection method, and the maximum transfer efficiency of the WPT system can reach 91%.

With the application of electrical equipment, magnetically coupled resonant (MCR) wireless power transfer (WPT) technology has become an effective means to improve equipment intelligence. The MCR-WPT system is a loosely coupled system, and the resonant frequency may be split or detuned due to the changes of load or transferring distance, resulting in the system transfer efficiency (TE) greatly reduced. To solve the problems of limited speed and accuracy in the existing frequency tracking methods, this paper analyzes the relation between the detuning rate and the system TE, proposing an adaptive frequency tracking control method based on fuzzy radial basis function neural network control. The neural network outputs proportion–integration–differentiation parameters to adjust the inverter drive circuit, and the frequency of inverter drive circuit is adjusted nonlinearly in real time to ensure the accurate frequency tracking of the MCR-WPT system. The simulation and experimental results show that the proposed method can enhance the tracking ability of the resonant frequency, and effectively improve the system TE.

Haze is one of the major factors that degrade outdoor images. Removing haze from an image is a challenge problem. In this paper, a two-peak channel prior model is proposed for general image dehazing. Firstly, the estimation of medium transmission function is derived and analyzed comprehensively. Secondly, a new calculation method estimating atmospheric light is proposed for more robust dehazing with a new compensation parameter. The experimental results illustrate that the proposed method is able to achieve more satisfied dehazing results than two state-of-the-art methods.