While Retrieval-Augmented Generation (RAG) effectively reduces hallucinations by integrating external knowledge bases, it introduces vulnerabilities to membership inference attacks (MIAs), particularly in systems handling sensitive data. Existing MIAs targeting RAG's external databases often rely on model responses but ignore the interference of non-member-retrieved documents on RAG outputs, limiting their effectiveness. To address this, we propose DCMI, a differential calibration MIA that mitigates the negative impact of non-member-retrieved documents. Specifically, DCMI leverages the sensitivity gap between member and non-member retrieved documents under query perturbation. It generates perturbed queries for calibration to isolate the contribution of member-retrieved documents while minimizing the interference from non-member-retrieved documents. Experiments under progressively relaxed assumptions show that DCMI consistently outperforms baselines--for example, achieving 97.42% AUC and 94.35% Accuracy against the RAG system with Flan-T5, exceeding the MBA baseline by over 40%. Furthermore, on real-world RAG platforms such as Dify and MaxKB, DCMI maintains a 10%-20% advantage over the baseline. These results highlight significant privacy risks in RAG systems and emphasize the need for stronger protection mechanisms. We appeal to the community's consideration of deeper investigations, like ours, against the data leakage risks in rapidly evolving RAG systems.

A central goal of artificial intelligence is to build systems that can understand and predict complex, evolving sequences of events. However, current foundation models, designed for natural language, fail to grasp the holistic nature of structured interactions found in domains like telecommunications, e-commerce and finance. By serializing events into text, they disassemble them into semantically fragmented parts, losing critical context. In this work, we introduce the Unified Interaction Foundation Model (UIFM), a foundation model engineered for genuine behavioral understanding. At its core is the principle of composite tokenization, where each multi-attribute event is treated as a single, semantically coherent unit. This allows UIFM to learn the underlying "grammar" of user behavior, perceiving entire interactions rather than a disconnected stream of data points. We demonstrate that this architecture is not just more accurate, but represents a fundamental step towards creating more adaptable and intelligent predictive systems.

Reinforcement learning (RL) has recently become the dominant paradigm for strengthening the reasoning abilities of large language models (LLMs). Yet the rule-based reward functions commonly used on mathematical or programming benchmarks assess only answer format and correctness, providing no signal as to whether the induced Chain-of-Thought (CoT) actually improves the answer. Furthermore, such task-specific training offers limited control over logical depth and therefore may fail to reveal a model's genuine reasoning capacity. We propose Dynamic Reasoning Efficiency Reward (DRER) -- a plug-and-play RL reward framework that reshapes both reward and advantage signals. (i) A Reasoning Quality Reward assigns fine-grained credit to those reasoning chains that demonstrably raise the likelihood of the correct answer, directly incentivising the trajectories with beneficial CoT tokens. (ii) A Dynamic Length Advantage decays the advantage of responses whose length deviates from a validation-derived threshold, stabilising training. To facilitate rigorous assessment, we also release Logictree, a dynamically constructed deductive reasoning dataset that functions both as RL training data and as a comprehensive benchmark. Experiments confirm the effectiveness of DRER: our 7B model attains GPT-o3-mini level performance on Logictree with 400 trianing steps, while the average confidence of CoT-augmented answers rises by 30%. The model further exhibits generalisation across diverse logical-reasoning datasets, and the mathematical benchmark AIME24. These results illuminate how RL shapes CoT behaviour and chart a practical path toward enhancing formal-reasoning skills in large language models. All code and data are available in repository https://github.com/Henryhe09/DRER.

With Large Language Models' (LLMs) emergent abilities on code generation tasks, Text-to-SQL has become one of the most popular downstream applications. Despite the strong results of multiple recent LLM-based Text-to-SQL frameworks, the research community often overlooks the importance of database schema information for generating high-quality SQL queries. We find that such schema information plays a significant or even dominant role in the Text-to-SQL task. To tackle this challenge, we propose a novel database schema expert with two components. We first introduce X-Linking, an LLM Supervised Finetuning (SFT)- based method that achieves superior Schema Linking results compared to existing open-source Text-to-SQL methods. In addition, we innovatively propose an X-Admin component that focuses on Schema Understanding by bridging the gap between abstract schema information and the user's natural language question. Aside from better learning with schema information, we experiment with Multi-LLMs for different components within the system to further boost its performance. By incorporating these techniques into our end-to-end framework, X-SQL, we have achieved Execution Accuracies of 84.9% on the Spider-Dev dataset and 82.5% on the Spider-Test dataset. This outstanding performance establishes X-SQL as the leading Text-to-SQL framework based on open-source models.

Large Language Models (LLMs) have seen rapid adoption in recent years, with industries increasingly relying on them to maintain a competitive advantage. These models excel at interpreting user instructions and generating human-like responses, leading to their integration across diverse domains, including consulting and information retrieval. However, their widespread deployment also introduces substantial security risks, most notably in the form of prompt injection and jailbreak attacks. To systematically evaluate LLM vulnerabilities -- particularly to external prompt injection -- we conducted a series of experiments on eight commercial models. Each model was tested without supplementary sanitization, relying solely on its built-in safeguards. The results exposed exploitable weaknesses and emphasized the need for stronger security measures. Four categories of attacks were examined: direct injection, indirect (external) injection, image-based injection, and prompt leakage. Comparative analysis indicated that Claude 3 demonstrated relatively greater robustness; nevertheless, empirical findings confirm that additional defenses, such as input normalization, remain necessary to achieve reliable protection.

Recent advances in large language models (LLMs) have fueled growing interest in automating geospatial analysis and GIS workflows, yet their actual capabilities remain uncertain. In this work, we call for rigorous evaluation of LLMs on well-defined geoprocessing tasks before making claims about full GIS automation. To this end, we present GeoAnalystBench, a benchmark of 50 Python-based tasks derived from real-world geospatial problems and carefully validated by GIS experts. Each task is paired with a minimum deliverable product, and evaluation covers workflow validity, structural alignment, semantic similarity, and code quality (CodeBLEU). Using this benchmark, we assess both proprietary and open source models. Results reveal a clear gap: proprietary models such as ChatGPT-4o-mini achieve high validity 95% and stronger code alignment (CodeBLEU 0.39), while smaller open source models like DeepSeek-R1-7B often generate incomplete or inconsistent workflows (48.5% validity, 0.272 CodeBLEU). Tasks requiring deeper spatial reasoning, such as spatial relationship detection or optimal site selection, remain the most challenging across all models. These findings demonstrate both the promise and limitations of current LLMs in GIS automation and provide a reproducible framework to advance GeoAI research with human-in-the-loop support.

Evaluating factual accuracy in Large Language Model (LLM)-generated clinical text is a critical barrier to adoption, as expert review is unscalable for the continuous quality assurance these systems require. We address this challenge with two complementary contributions. First, we introduce MedFactEval, a framework for scalable, fact-grounded evaluation where clinicians define high-salience key facts and an "LLM Jury"--a multi-LLM majority vote--assesses their inclusion in generated summaries. Second, we present MedAgentBrief, a model-agnostic, multi-step workflow designed to generate high-quality, factual discharge summaries. To validate our evaluation framework, we established a gold-standard reference using a seven-physician majority vote on clinician-defined key facts from inpatient cases. The MedFactEval LLM Jury achieved almost perfect agreement with this panel (Cohen's kappa=81%), a performance statistically non-inferior to that of a single human expert (kappa=67%, P < 0.001). Our work provides both a robust evaluation framework (MedFactEval) and a high-performing generation workflow (MedAgentBrief), offering a comprehensive approach to advance the responsible deployment of generative AI in clinical workflows.

Traditional Chinese Medicine (TCM) formulas play a significant role in treating epidemics and complex diseases. Existing models for TCM utilize traditional algorithms or deep learning techniques to analyze formula relationships, yet lack comprehensive results, such as complete formula compositions and detailed explanations. Although recent efforts have used TCM instruction datasets to fine-tune Large Language Models (LLMs) for explainable formula generation, existing datasets lack sufficient details, such as the roles of the formula's sovereign, minister, assistant, courier; efficacy; contraindications; tongue and pulse diagnosis-limiting the depth of model outputs. To address these challenges, we propose ZhiFangDanTai, a framework combining Graph-based Retrieval-Augmented Generation (GraphRAG) with LLM fine-tuning. ZhiFangDanTai uses GraphRAG to retrieve and synthesize structured TCM knowledge into concise summaries, while also constructing an enhanced instruction dataset to improve LLMs' ability to integrate retrieved information. Furthermore, we provide novel theoretical proofs demonstrating that integrating GraphRAG with fine-tuning techniques can reduce generalization error and hallucination rates in the TCM formula task. Experimental results on both collected and clinical datasets demonstrate that ZhiFangDanTai achieves significant improvements over state-of-the-art models. Our model is open-sourced at https://huggingface.co/tczzx6/ZhiFangDanTai1.0.

We give an overview on the emerging applications of GenAI in the financial industry, especially within investment banks. Inherent to these exciting opportunities is a new realm of risks that must be managed properly. By heeding both the Yin and Yang sides of GenAI, we can accelerate its organic growth while safeguarding the entire financial industry during this nascent era of AI.

With the evolution of generative AI, multi - agent systems leveraging large - language models(LLMs) have emerged as a powerful tool for complex tasks. However, these systems face challenges in quantifying agent performance and lack mechanisms to assess agent credibility. To address these issues, we introduce DRF, a dynamic reputation filtering framework. DRF constructs an interactive rating network to quantify agent performance, designs a reputation scoring mechanism to measure agent honesty and capability, and integrates an Upper Confidence Bound - based strategy to enhance agent selection efficiency. Experiments show that DRF significantly improves task completion quality and collaboration efficiency in logical reasoning and code - generation tasks, offering a new approach for multi - agent systems to handle large - scale tasks.