The emergence of large language models (LLMs) has significantly advanced the development of natural language processing (NLP), especially in text generation tasks like question answering. However, model hallucinations remain a major challenge in natural language generation (NLG) tasks due to their complex causes. We systematically expand on the causes of factual hallucinations from the perspective of knowledge shortcuts, analyzing hallucinations arising from correct and defect-free data and demonstrating that knowledge-shortcut hallucinations are prevalent in generative models. To mitigate this issue, we propose a high similarity pruning algorithm at the data preprocessing level to reduce spurious correlations in the data. Additionally, we design a specific detection method for knowledge-shortcut hallucinations to evaluate the effectiveness of our mitigation strategy. Experimental results show that our approach effectively reduces knowledge-shortcut hallucinations, particularly in fine-tuning tasks, without negatively impacting model performance in question answering. This work introduces a new paradigm for mitigating specific hallucination issues in generative models, enhancing their robustness and reliability in real-world applications.

Using large language models (LLMs) integration platforms without transparency about which LLM is being invoked can lead to potential security risks. Specifically, attackers may exploit this black-box scenario to deploy malicious models and embed viruses in the code provided to users. In this context, it is increasingly urgent for users to clearly identify the LLM they are interacting with, in order to avoid unknowingly becoming victims of malicious models. However, existing studies primarily focus on mixed classification of human and machine-generated text, with limited attention to classifying texts generated solely by different models. Current research also faces dual bottlenecks: poor quality of LLM-generated text (LLMGT) datasets and limited coverage of detectable LLMs, resulting in poor detection performance for various LLMGT in black-box scenarios. We propose the first LLMGT fingerprint detection model, \textbf{FDLLM}, based on Qwen2.5-7B and fine-tuned using LoRA to address these challenges. FDLLM can more efficiently handle detection tasks across multilingual and multi-domain scenarios. Furthermore, we constructed a dataset named \textbf{FD-Datasets}, consisting of 90,000 samples that span multiple languages and domains, covering 20 different LLMs. Experimental results demonstrate that FDLLM achieves a macro F1 score 16.7\% higher than the best baseline method, LM-D.

Word frequency is a key variable in psycholinguistics, useful for modeling human familiarity with words even in the era of large language models (LLMs). Frequency in film subtitles has proved to be a particularly good approximation of everyday language exposure. For many languages, however, film subtitles are not easily available, or are overwhelmingly translated from English. We demonstrate that frequencies extracted from carefully processed YouTube subtitles provide an approximation comparable to, and often better than, the best currently available resources. Moreover, they are available for languages for which a high-quality subtitle or speech corpus does not exist. We use YouTube subtitles to construct frequency norms for five diverse languages, Chinese, English, Indonesian, Japanese, and Spanish, and evaluate their correlation with lexical decision time, word familiarity, and lexical complexity. In addition to being strongly correlated with two psycholinguistic variables, a simple linear regression on the new frequencies achieves a new high score on a lexical complexity prediction task in English and Japanese, surpassing both models trained on film subtitle frequencies and the LLM GPT-4. Our code, the frequency lists, fastText word embeddings, and statistical language models are freely available at https://github.com/naist-nlp/tubelex.

In recent years, Artificial Intelligence Weather Prediction (AIWP) models have achieved performance comparable to, or even surpassing, traditional Numerical Weather Prediction (NWP) models by leveraging reanalysis data. However, a less-explored approach involves training AIWP models directly on observational data, enhancing computational efficiency and improving forecast accuracy by reducing the uncertainties introduced through data assimilation processes. In this study, we propose OMG-HD, a novel AI-based regional high-resolution weather forecasting model designed to make predictions directly from observational data sources, including surface stations, radar, and satellite, thereby removing the need for operational data assimilation. Our evaluation shows that OMG-HD outperforms both the European Centre for Medium-Range Weather Forecasts (ECMWF)'s high-resolution operational forecasting system, IFS-HRES, and the High-Resolution Rapid Refresh (HRRR) model at lead times of up to 12 hours across the contiguous United States (CONUS) region. We achieve up to a 13% improvement on RMSE for 2-meter temperature, 17% on 10-meter wind speed, 48% on 2-meter specific humidity, and 32% on surface pressure compared to HRRR. Our method shows that it is possible to use AI-driven approaches for rapid weather predictions without relying on NWP-derived weather fields as model input. This is a promising step towards using observational data directly to make operational forecasts with AIWP models.

The forecasting skill of numerical weather prediction (NWP) models critically depends on the accurate initial conditions, also known as analysis, provided by data assimilation (DA). Traditional DA methods often face a trade-off between computational cost and accuracy due to complex linear algebra computations and the high dimensionality of the model, especially in nonlinear systems. Moreover, processing massive data in real-time requires substantial computational resources. To address this, we introduce an artificial intelligence-based data assimilation framework (ADAF) to generate high-quality kilometer-scale analysis. This study is the pioneering work using real-world observations from varied locations and multiple sources to verify the AI method's efficacy in DA, including sparse surface weather observations and satellite imagery. We implemented ADAF for four near-surface variables in the Contiguous United States (CONUS). The results indicate that ADAF surpasses the High Resolution Rapid Refresh Data Assimilation System (HRRRDAS) in accuracy by 16% to 33% for near-surface atmospheric conditions, aligning more closely with actual observations, and can effectively reconstruct extreme events, such as tropical cyclone wind fields. Sensitivity experiments reveal that ADAF can generate high-quality analysis even with low-accuracy backgrounds and extremely sparse surface observations. ADAF can assimilate massive observations within a three-hour window at low computational cost, taking about two seconds on an AMD MI200 graphics processing unit (GPU). ADAF has been shown to be efficient and effective in real-world DA, underscoring its potential role in operational weather forecasting.

Testing of function safety and Safety Of The Intended Functionality (SOTIF) is important for autonomous vehicles (AVs). It is hard to test the AV's hazard response in the real world because it would involve hazards to passengers and other road users. This paper studied on virtual testing of AV on the CARLA platform and proposed a Humanoid Scenario Generation (HSG) scheme to investigate the impacts of hazardous behaviors on AV collision rates. The HSG scheme breakthrough the current limitation on the rarity and reproducibility of real scenes. By accurately capturing five prominent human driver behaviors that directly contribute to vehicle collisions in the real world, the methodology significantly enhances the realism and diversity of the simulation, as evidenced by collision rate statistics across various traffic scenarios. Thus, the modular framework allows for customization, and its seamless integration within the CARLA platform ensures compatibility with existing tools. Ultimately, the comparison results demonstrate that all vehicles that exhibited hazardous behaviors followed the predefined random speed distribution and the effectiveness of the HSG was validated by the distinct characteristics displayed by these behaviors.