With the growing importance of content safety, toxic language detection, especially in Chinese online environments, has become a key task in natural language processing. However, real-world toxic expressions often appear in obfuscated forms such as pinyin abbreviations, symbol insertion, or visually similar substitutions, making them difficult to detect using traditional rule-based or static models. To address this challenge, we propose a dynamic knowledge graph construction method for toxic text variants, named Variant-KG. This graph encodes diverse structural relations between canonical toxic terms and their variants based on phonetic similarity, visual resemblance, and contextual co-occurrence. A small amount of labeled data is further used to fine-tune large language models (LLMs), enabling initial normalization and variant recognition. On top of this, we design a collaborative detection framework that combines the Variant-KG with frozen LLMs. It performs graph augmented prompting for structure-aware reasoning and adopts a Think-Search-Generate paradigm to dynamically recover broken paths when graph connections are incomplete, enabling both data self-enhancement and knowledge completion during inference. Evaluations on multiple Chinese toxic language datasets show that our model consistently outperforms both non-knowledge-enhanced and existing knowledge-enhanced baselines, demonstrating the effectiveness of our proposed dynamic reasoning framework in handling diverse toxic expressions.

The increasing prevalence of large language models (LLMs) has significantly advanced text generation, but the human-like quality of LLM outputs presents major challenges in reliably distinguishing between human-authored and LLM-generated texts. Existing detection benchmarks are constrained by their reliance on static datasets, scenario-specific tasks (e.g., question answering and text refinement), and a primary focus on English, overlooking the diverse linguistic and operational subtleties of LLMs. To address these gaps, we propose CUDRT, a comprehensive evaluation framework and bilingual benchmark in Chinese and English, categorizing LLM activities into five key operations: Create, Update, Delete, Rewrite, and Translate. CUDRT provides extensive datasets tailored to each operation, featuring outputs from state-of-the-art LLMs to assess the reliability of LLM-generated text detectors. This framework supports scalable, reproducible experiments and enables in-depth analysis of how operational diversity, bilingual training sets, and LLM architectures influence detection performance. Our extensive experiments demonstrate the framework’s capacity to optimize detection systems and provide practical guidance for training model-based detectors, revealing that training on specific operations and outputs from certain LLMs significantly improves model-based detector generalization. By advancing robust methodologies for identifying LLM-generated texts, this work contributes to the development of intelligent systems capable of meeting real-world bilingual detection challenges. Source code and dataset are available at GitHub.

Text style transfer plays a vital role in online entertainment and social media. However, existing models struggle to handle the complexity of Chinese long texts, such as rhetoric, structure, and culture, which restricts their broader application. To bridge this gap, we propose a Chinese Article-style Transfer (CAT-LLM) framework, which addresses the challenges of style transfer in complex Chinese long texts. At its core, CAT-LLM features a bespoke pluggable Text Style Definition (TSD) module that integrates machine learning algorithms to analyze and model article styles at both word and sentence levels. This module acts as a bridge, enabling large language models (LLMs) to better understand and adapt to the complexities of Chinese article styles. Furthermore, it supports the dynamic expansion of internal style trees, enabling the framework to seamlessly incorporate new and diverse style definitions, enhancing adaptability and scalability for future research and applications. Additionally, to facilitate robust evaluation, we created 10 parallel datasets using a combination of ChatGPT and various Chinese texts, each corresponding to distinct writing styles, significantly improving the accuracy of the model evaluation and establishing a novel paradigm for text style transfer research. Extensive experimental results demonstrate that CAT-LLM, combined with GPT-3.5-Turbo, achieves state-of-the-art performance, with a transfer accuracy F1 score of 79.36% and a content preservation F1 score of 96.47% on the “Fortress Besieged” dataset. These results highlight CAT-LLM’s innovative contributions to style transfer research, including its ability to preserve content integrity while achieving precise and flexible style transfer across diverse Chinese text domains. Building on these contributions, CAT-LLM presents significant potential for advancing Chinese digital media and facilitating automated content creation. Source code is available at GitHub ( https://github.com/TaoZhen1110/CAT-LLM ).

Designing pre-training objectives that more closely resemble the downstream tasks for pre-trained language models can lead to better performance at the fine-tuning stage, especially in the ad-hoc retrieval area. Existing pre-training approaches tailored for IR tried to incorporate weak supervised signals, such as query-likelihood based sampling, to construct pseudo query-document pairs from the raw textual corpus. However, these signals rely heavily on the sampling method. For example, the query likelihood model may lead to much noise in the constructed pre-training data. In this paper, we propose to leverage the large-scale hyperlinks and anchor texts to pre-train the language model for ad-hoc retrieval. Since the anchor texts are created by webmasters and can usually summarize the target document, it can help to build more accurate and reliable pre-training samples than a specific algorithm. Considering different views of the downstream ad-hoc retrieval, we devise four pre-training tasks based on the hyperlinks. We then pre-train the Transformer model to predict the pair-wise preference, jointly with the Masked Language Model objective. Experimental results on two large-scale ad-hoc retrieval datasets show the significant improvement of our model compared with the existing methods.

In recent decades, commodities have attracted the attention of a large number of investors and financial professionals, and their prices have become very important for investors and policy makers. Although natural gas is widely used as a clean energy, there is less literature on price research and most of them use historical prices and fundamental factors to analyze natural gas price. Based on historical prices, this paper analyzes whether internet search data and news sentiment can improve forecasting ability, and compare which can achieve better prediction results. The experimental results show that both internet search and news sentiment contain additional information to improve the prediction effect, and internet search data can achieve better prediction results.