Large Language Models (LLMs) often generate overconfident yet factually incorrect hallucinations. Current detection paradigms suffer from a trade-off between the high accuracy of computationally expensive black-box methods and the inability of white-box methods to detect stubborn hallucinations. To bridge this gap, we propose GHOST (Geometric Hidden-state Observation for Semantic Truthfulness), an efficient white-box framework for hallucination detection in LLMs. We primarily target confused hallucinations marked by internal reasoning instability, while also capturing stubborn hallucinations characterized by premature layer-wise convergence as a complementary signal. By integrating internal geometric dynamics with output probability distributions, GHOST constructs a high-dimensional feature space for non-linear truthfulness classification. Extensive evaluations on FinanceBench, RAGTruth, HaluEval, and PopQA show that GHOST outperforms white-box baselines and achieves competitive black-box performance while reducing computational overhead by over 90%, offering a robust solution for real-time detection.

Two-step approaches combining pre-trained large language model embeddings and anomaly detectors demonstrate strong performance in text anomaly detection by leveraging rich semantic representations. However, high-dimensional dense embeddings extracted by large language models pose challenges due to substantial memory requirements and high computation time. To address this challenge, we introduce the Simplified Isolation Kernel (SIK), which maps high-dimensional dense embeddings to lower-dimensional sparse representations while preserving crucial anomaly characteristics. SIK has linear-time complexity and significantly reduces space complexity through its innovative boundary-focused feature mapping.Experiments across 7 datasets demonstrate that SIK achieves better detection performance than 11 SOTA anomaly detection algorithms while maintaining computational efficiency and low memory cost. All code and demonstrations are available at https://github.com/charles-cao/SIK.

Self-disclosure can provide psychological comfort and social support, but it also carries the risk of unintentionally revealing sensitive information, leading to serious privacy concerns. Research on self-disclosure in Chinese multimodal contexts remains limited, lacking high-quality corpora, analysis, and methods for detection. This work focuses on self-disclosure behaviors on Chinese multimodal social media platforms and constructs a high-quality text-image corpus to address this critical data gap. We systematically analyze the distribution of self-disclosure types, modality preferences, and their relationship with user intent, uncovering expressive patterns unique to the Chinese multimodal context. We also fine-tune five multimodal large language models to enhance self-disclosure detection in multimodal scenarios. Among these models, the Qwen2.5-omni-7B achieved a strong performance, with a partial span F1 score of 88.2%. This study provides a novel research perspective on multimodal self-disclosure in the Chinese context.

With the popularity of large language models and their high-quality text generation capabilities, researchers are using them as auxiliary tools for text summary writing. Although summaries generated by these large language models are smooth and capture key information sufficiently, the quality of their output depends on the prompt, and the generated text is somewhat procedural to a certain extent. We construct LecSumm to verify whether language models truly capture human writing preferences, in which we recruit 200 college students to write summaries for lecture notes on ten different machine-learning topics and analyze writing preferences in real-world human summaries through the dimensions of length, content depth, tone & style, and summary format. We define the method of capturing human writing preferences by language models as finetuning pre-trained models with data and designing prompts to optimize the output of large language models. The results of translating the analyzed human writing preferences into prompts and conducting experiments show that both models still fail to capture human writing preferences effectively. Our LecSumm dataset brings new challenges to finetuned and prompt-based large language models on the task of human-centered text summarization.

With the popularity of large language models (LLMs) and their ability to handle longer input documents, there is a growing need for high-quality long document summarization datasets. Although many models already support 16k input, current lengths of summarization datasets are inadequate, and salient information is not evenly distributed. To bridge these gaps, we collect a new summarization dataset called SumSurvey, consisting of more than 18k scientific survey papers. With an average document length exceeding 12k and a quarter exceeding 16k, as well as the uniformity metric outperforming current mainstream long document summarization datasets, SumSurvey brings new challenges and expectations to both fine-tuned models and LLMs. The informativeness of summaries and the models supporting the evaluation of long document summarization warrant further attention. Automatic and human evaluation results on this abstractive dataset confirm this view. Our dataset and code are available at https://github.com/Oswald1997/SumSurvey.

Early detection and automated classification of dementia has recently gained considerable attention using neuroimaging data and spontaneous speech. In this paper, we validate the possibility of dementia detection with in-hospital clinical notes. We collected 954 patients’ clinical notes from a local hospital and assign dementia/non-dementia labels to those patients based on clinical assessment and telephone interview. Given the labeled dementia data sets, we fine tune a ClinicalBioBERT based on some filtered clinical notes and conducted experiments on both binary and three class dementia classification. Our experiment results show that the fine tuned ClinicalBioBERT achieved satisfied performance on binary classification but failed on three class dementia classification. Further analysis suggests that more human prior knowledge should be considered.