Tool-augmented large language models (LLMs) are increasingly employed in real-world applications, but tool usage errors still hinder their reliability. We introduce ToolCritic, a diagnostic framework that evaluates and improves LLM behavior in multi-turn, tool-augmented dialogues. ToolCritic detects eight distinct error types specific to tool-calling (e.g., premature invocation, argument misalignment, and misinterpretation of tool outputs) and provides targeted feedback to the main LLM. The main LLM, assumed to have strong reasoning, task understanding and orchestration capabilities, then revises its response based on ToolCritic's feedback. We systematically define these error categories and construct a synthetic dataset to train ToolCritic. Experimental results on the Schema-Guided Dialogue (SGD) dataset demonstrate that ToolCritic improves tool-calling accuracy by up to 13% over baselines, including zero-shot prompting and self-correction techniques. This represents a promising step toward more robust LLM integration with external tools in real-world dialogue applications.

Knowledge Distillation (KD) accelerates training of large language models (LLMs) but poses intellectual property protection and LLM diversity risks. Existing KD detection methods based on self-identity or output similarity can be easily evaded through prompt engineering. We present a KD detection framework effective in both white-box and black-box settings by exploiting an overlooked signal: the transfer of MoE "structural habits", especially internal routing patterns. Our approach analyzes how different experts specialize and collaborate across various inputs, creating distinctive fingerprints that persist through the distillation process. To extend beyond the white-box setup and MoE architectures, we further propose Shadow-MoE, a black-box method that constructs proxy MoE representations via auxiliary distillation to compare these patterns between arbitrary model pairs. We establish a comprehensive, reproducible benchmark that offers diverse distilled checkpoints and an extensible framework to facilitate future research. Extensive experiments demonstrate >94% detection accuracy across various scenarios and strong robustness to prompt-based evasion, outperforming existing baselines while highlighting the structural habits transfer in LLMs.

Multimodal molecular representation learning, which jointly models molecular graphs and their textual descriptions, enhances predictive accuracy and interpretability by enabling more robust and reliable predictions of drug toxicity, bioactivity, and physicochemical properties through the integration of structural and semantic information. However, existing multimodal methods suffer from two key limitations: (1) they typically perform cross-modal interaction only at the final encoder layer, thus overlooking hierarchical semantic dependencies; (2) they lack a unified prototype space for robust alignment between modalities. To address these limitations, we propose ProtoMol, a prototype-guided multimodal framework that enables fine-grained integration and consistent semantic alignment between molecular graphs and textual descriptions. ProtoMol incorporates dual-branch hierarchical encoders, utilizing Graph Neural Networks to process structured molecular graphs and Transformers to encode unstructured texts, resulting in comprehensive layer-wise representations. Then, ProtoMol introduces a layer-wise bidirectional cross-modal attention mechanism that progressively aligns semantic features across layers. Furthermore, a shared prototype space with learnable, class-specific anchors is constructed to guide both modalities toward coherent and discriminative representations. Extensive experiments on multiple benchmark datasets demonstrate that ProtoMol consistently outperforms state-of-the-art baselines across a variety of molecular property prediction tasks.

This study presents a three-step machine learning framework to predict bubbles in the S&P 500 stock market by combining financial news sentiment with macroeconomic indicators. Building on traditional econometric approaches, the proposed approach predicts bubble formation by integrating textual and quantitative data sources. In the first step, bubble periods in the S&P 500 index are identified using a right-tailed unit root test, a widely recognized real-time bubble detection method. The second step extracts sentiment features from large-scale financial news articles using natural language processing (NLP) techniques, which capture investor's expectations and behavioral patterns. In the final step, ensemble learning methods are applied to predict bubble occurrences based on both sentiment-based and macroeconomic predictors. Model performance is evaluated through k-fold cross-validation and compared against benchmark machine learning algorithms. Empirical results indicate that the proposed three-step ensemble approach significantly improves predictive accuracy and robustness, providing valuable early warning insights for investors, regulators, and policymakers in mitigating systemic financial risks.

Life satisfaction is a crucial facet of human well-being. Hence, research on life satisfaction is incumbent for understanding how individuals experience their lives and influencing interventions targeted at enhancing mental health and well-being. Life satisfaction has traditionally been measured using analog, complicated, and frequently error-prone methods. These methods raise questions concerning validation and propagation. However, this study demonstrates the potential for machine learning algorithms to predict life satisfaction with a high accuracy of 93.80% and a 73.00% macro F1-score. The dataset comes from a government survey of 19000 people aged 16-64 years in Denmark. Using feature learning techniques, 27 significant questions for assessing contentment were extracted, making the study highly reproducible, simple, and easily interpretable. Furthermore, clinical and biomedical large language models (LLMs) were explored for predicting life satisfaction by converting tabular data into natural language sentences through mapping and adding meaningful counterparts, achieving an accuracy of 93.74% and macro F1-score of 73.21%. It was found that life satisfaction prediction is more closely related to the biomedical domain than the clinical domain. Ablation studies were also conducted to understand the impact of data resampling and feature selection techniques on model performance. Moreover, the correlation between primary determinants with different age brackets was analyzed, and it was found that health condition is the most important determinant across all ages. This study demonstrates how machine learning, large language models and XAI can jointly contribute to building trust and understanding in using AI to investigate human behavior, with significant ramifications for academics and professionals working to quantify and comprehend subjective well-being.

Large Language Model (LLM) providers expose fine-tuning APIs that let end users fine-tune their frontier LLMs. Unfortunately, it has been shown that an adversary with fine-tuning access to an LLM can bypass safeguards. Particularly concerning, such attacks may avoid detection with datasets that are only implicitly harmful. Our work studies robust detection mechanisms for adversarial use of fine-tuning APIs. We introduce the concept of a fine-tuning auditing agent and show it can detect harmful fine-tuning prior to model deployment. We provide our auditing agent with access to the fine-tuning dataset, as well as the fine-tuned and pre-fine-tuned models, and request the agent assigns a risk score for the fine-tuning job. We evaluate our detection approach on a diverse set of eight strong fine-tuning attacks from the literature, along with five benign fine-tuned models, totaling over 1400 independent audits. These attacks are undetectable with basic content moderation on the dataset, highlighting the challenge of the task. With the best set of affordances, our auditing agent achieves a 56.2% detection rate of adversarial fine-tuning at a 1% false positive rate. Most promising, the auditor is able to detect covert cipher attacks that evade safety evaluations and content moderation of the dataset. While benign fine-tuning with unintentional subtle safety degradation remains a challenge, we establish a baseline configuration for further work in this area. We release our auditing agent at https://github.com/safety-research/finetuning-auditor.

Machine learning models trained on imbalanced datasets often exhibit intersectional biases--systematic errors arising from the interaction of multiple attributes such as object class and environmental conditions. This paper presents a data-driven framework for analyzing and mitigating such biases in image classification. We introduce the Intersec-tional Fairness Evaluation Framework (IFEF), which combines quantitative fairness metrics with interpretability tools to systematically identify bias patterns in model predictions. Building on this analysis, we propose Bias-Weighted Augmentation (BWA), a novel data augmentation strategy that adapts transformation intensities based on subgroup distribution statistics. Experiments on the Open Images V7 dataset with five object classes demonstrate that BWA improves accuracy for underrep-resented class-environment intersections by up to 24 percentage points while reducing fairness metric disparities by 35%. Statistical analysis across multiple independent runs confirms the significance of improvements (p < 0.05). Our methodology provides a replicable approach for analyzing and addressing intersectional biases in image classification systems.

Artificial intelligence surrogates are systems designed to infer preferences when individuals lose decision-making capacity. Fairness in such systems is a domain that has been insufficiently explored. Traditional algorithmic fairness frameworks are insufficient for contexts where decisions are relational, existential, and culturally diverse. This paper explores an ethical framework for algorithmic fairness in AI surrogates by mapping major fairness notions onto potential real-world end-of-life scenarios. It then examines fairness across moral traditions. The authors argue that fairness in this domain extends beyond parity of outcomes to encompass moral representation, fidelity to the patient's values, relationships, and worldview.

This study investigates the privacy risks associated with diffusion-based synthetic tabular data generation methods, focusing on their susceptibility to Membership Inference Attacks (MIAs). We examine two recent models, TabDDPM and TabSyn, by developing query-based MIAs based on the step-wise error comparison method. Our findings reveal that TabDDPM is more vulnerable to these attacks. TabSyn exhibits resilience against our attack models. Our work underscores the importance of evaluating the privacy implications of diffusion models and encourages further research into robust privacy-preserving mechanisms for synthetic data generation.

Billions of dollars are lost every year in DeFi platforms by transactions exploiting business logic or accounting vulnerabilities. Existing defenses focus on static code analysis, public mempool screening, attacker contract detection, or trusted off-chain monitors, none of which prevents exploits submitted through private relays or malicious contracts that execute within the same block. We present the first decentralized, fully on-chain learning framework that: (i) performs gas-prohibitive computation on Layer-2 to reduce cost, (ii) propagates verified model updates to Layer-1, and (iii) enables gas-bounded, low-latency inference inside smart contracts. A novel Proof-of-Improvement (PoIm) protocol governs the training process and verifies each decentralized micro update as a self-verifying training transaction. Updates are accepted by \textit{PoIm} only if they demonstrably improve at least one core metric (e.g., accuracy, F1-score, precision, or recall) on a public benchmark without degrading any of the other core metrics, while adversarial proposals get financially penalized through an adaptable test set for evolving threats. We develop quantization and loop-unrolling techniques that enable inference for logistic regression, SVM, MLPs, CNNs, and gated RNNs (with support for formally verified decision tree inference) within the Ethereum block gas limit, while remaining bit-exact to their off-chain counterparts, formally proven in Z3. We curate 298 unique real-world exploits (2020 - 2025) with 402 exploit transactions across eight EVM chains, collectively responsible for \$3.74 B in losses.