Chain-of-thought (CoT) distillation aims to enhance small language models' (SLMs) reasoning by transferring multi-step reasoning capability from the larger teacher models. However, existing work underestimates rationale quality, focusing primarily on data quantity, which may transfer noisy or incorrect information to the student model. To address the above issues, we proposed \textbf{M}odel-\textbf{O}riented \textbf{R}ationale \textbf{S}election \textbf{D}istillation (MoRSD), which can discern and select high quality rationales for distillation to improve performance further. We further propose a Rationale Difficulty (RD) metric to measure the ability of the student model to generate the correct answer under a given rationale. Compared to the baseline, we achieved 4.6$\%$ average improvement on seven datasets over three tasks, using fewer rationales by controlling their accuracy, diversity, and difficulty. Our results reveal that a small portion of the high quality rationales can enhance the reasoning ability of student models than the entire dataset. Our method promises to be a possible solution for efficient CoT distillation. Our code will be released in https://github.com/Leon221220/MoRSD.

Artificial intelligence technology plays a crucial role in recommending prescriptions for traditional Chinese medicine (TCM). Previous studies have made significant progress by focusing on the symptom-herb relationship in prescriptions. However, several limitations hinder model performance: (i) Insufficient attention to patient-personalized information such as age, BMI, and medical history, which hampers accurate identification of syndrome and reduces efficacy. (ii) The typical long-tailed distribution of herb data introduces training biases and affects generalization ability. (iii) The oversight of the 'monarch, minister, assistant and envoy' compatibility among herbs increases the risk of toxicity or side effects, opposing the 'treatment based on syndrome differentiation' principle in clinical TCM. Therefore, we propose a novel hierarchical structure-enhanced personalized recommendation model for TCM formulas based on knowledge graph diffusion guidance, namely TCM-HEDPR. Specifically, we pre-train symptom representations using patient-personalized prompt sequences and apply prompt-oriented contrastive learning for data augmentation. Furthermore, we employ a KG-guided homogeneous graph diffusion method integrated with a self-attention mechanism to globally capture the non-linear symptom-herb relationship. Lastly, we design a heterogeneous graph hierarchical network to integrate herbal dispensing relationships with implicit syndromes, guiding the prescription generation process at a fine-grained level and mitigating the long-tailed herb data distribution problem. Extensive experiments on two public datasets and one clinical dataset demonstrate the effectiveness of TCM-HEDPR. In addition, we incorporate insights from modern medicine and network pharmacology to evaluate the recommended prescriptions comprehensively. It can provide a new paradigm for the recommendation of modern TCM.

Large language models (LLMs) have demonstrated remarkable capabilities, yet they also introduce novel security challenges. For instance, prompt jailbreaking attacks involve adversaries crafting sophisticated prompts to elicit responses from LLMs that deviate from human values. To uncover vulnerabilities in LLM alignment methods, we propose the PASS framework (\underline{P}rompt J\underline{a}ilbreaking via \underline{S}emantic and \underline{S}tructural Formalization). Specifically, PASS employs reinforcement learning to transform initial jailbreak prompts into formalized descriptions, which enhances stealthiness and enables bypassing existing alignment defenses. The jailbreak outputs are then structured into a GraphRAG system that, by leveraging extracted relevant terms and formalized symbols as contextual input alongside the original query, strengthens subsequent attacks and facilitates more effective jailbreaks. We conducted extensive experiments on common open-source models, demonstrating the effectiveness of our attack.

Antimicrobial Resistance (AMR) is a rapidly escalating global health crisis. While genomic sequencing enables rapid prediction of resistance phenotypes, current computational methods have limitations. Standard machine learning models treat the genome as an unordered collection of features, ignoring the sequential context of Single Nucleotide Polymorphisms (SNPs). State-of-the-art sequence models like Transformers are often too data-hungry and computationally expensive for the moderately-sized datasets that are typical in this domain. To address these challenges, we propose AMR-EnsembleNet, an ensemble framework that synergistically combines sequence-based and feature-based learning. We developed a lightweight, custom 1D Convolutional Neural Network (CNN) to efficiently learn predictive sequence motifs from high-dimensional SNP data. This sequence-aware model was ensembled with an XGBoost model, a powerful gradient boosting system adept at capturing complex, non-local feature interactions. We trained and evaluated our framework on a benchmark dataset of 809 E. coli strains, predicting resistance across four antibiotics with varying class imbalance. Our 1D CNN-XGBoost ensemble consistently achieved top-tier performance across all the antibiotics, reaching a Matthews Correlation Coefficient (MCC) of 0.926 for Ciprofloxacin (CIP) and the highest Macro F1-score of 0.691 for the challenging Gentamicin (GEN) AMR prediction. We also show that our model consistently focuses on SNPs within well-known AMR genes like fusA and parC, confirming it learns the correct genetic signals for resistance. Our work demonstrates that fusing a sequence-aware 1D CNN with a feature-based XGBoost model creates a powerful ensemble, overcoming the limitations of using either an order-agnostic or a standalone sequence model.

Medical dictation systems are essential tools in modern healthcare, enabling accurate and efficient conversion of speech into written medical documentation. The main objective of this paper is to create a domain-specific system for Greek medical speech transcriptions. The ultimate goal is to assist healthcare professionals by reducing the overload of manual documentation and improving workflow efficiency. Towards this goal, we develop a system that combines automatic speech recognition techniques with text correction model, allowing better handling of domain-specific terminology and linguistic variations in Greek. Our approach leverages both acoustic and textual modeling to create more realistic and reliable transcriptions. We focused on adapting existing language and speech technologies to the Greek medical context, addressing challenges such as complex medical terminology and linguistic inconsistencies. Through domain-specific fine-tuning, our system achieves more accurate and coherent transcriptions, contributing to the development of practical language technologies for the Greek healthcare sector.

Multimodal data are prevalent across various domains, and learning robust representations of such data is paramount to enhancing generation quality and downstream task performance. To handle heterogeneity and interconnections among different modalities, recent multimodal generative models extract shared and private (modality-specific) information with two separate variables. Despite attempts to enforce disentanglement between these two variables, these methods struggle with challenging datasets where the likelihood model is insufficient. In this paper, we propose Information-disentangled Multimodal V AE (IDMV AE) to explicitly address this issue, with rigorous mutual information-based regularizations, including cross-view mutual information maximization for extracting shared variables, and a cycle-consistency style loss for redundancy removal using generative augmentations. We further introduce diffusion models to improve the capacity of latent priors. These newly proposed components are complementary to each other. Compared to existing approaches, IDMV AE shows a clean separation between shared and private information, demonstrating superior generation quality and semantic coherence on challenging datasets. In addition to these naturally occurring data, synthetic multi-view data constructed from semantically similar input components or via augmentation are also widely used to learn useful representations for downstream tasks (V eliˇ ckovi c et al., 2019; Chen et al., 2020b; Caron et al., 2020; Tian et al., 2020a; Bardes et al., 2022).

The LLM-as-a-judge paradigm is widely used in both evaluating free-text model responses and reward modeling for model alignment and finetuning. Recently, finetuning judges with judge-specific data has emerged as an often preferred choice over directly prompting frontier models as judges, as the former achieves better performance with smaller model sizes while being more robust to common biases. However, the standard evaluation ignores several practical concerns of finetuned judges regarding their real world deployment. In this paper, we identify and formalize three aspects that affect the shelf life of these judges: future proofing and backward compatibility - how well judges finetuned on responses by today's generator models perform on responses by future models or past models, as well as question generalization - how well judges generalize to unseen questions at test time. We study these three aspects in the math domain under a unified framework with varying train and test distributions, three SFT - and DPO-based finetun-ing algorithms and three different base models. Experiments suggest that future-proofing is challenging for most models, while backward compatibility is relatively easy, with DPO-trained models consistently improving performance. We further find that continual learning provides a more balanced adaptation to shifts between older and newer response distributions than training solely on stronger or weaker responses. Moreover, all models observe certain degrees of performance degradation when moving from questions seen during training to unseen ones, showing that current judges do not fully generalize to unseen questions. These findings provide insights into practical considerations for developing and deploying judge models in the face of ever-changing generators. Automatic evaluators have become a central part of the large language model (LLM) development cycle.

Retrieval-Augmented Generation (RAG) enhances Large Language Models by grounding their outputs in external documents. These systems, however, remain vulnerable to attacks on the retrieval corpus, such as prompt injection. RAG-based search systems (e.g., Google's Search AI Overview) present an interesting setting for studying and protecting against such threats, as defense algorithms can benefit from built-in reliability signals -- like document ranking -- and represent a non-LLM challenge for the adversary due to decades of work to thwart SEO. Motivated by, but not limited to, this scenario, this work introduces ReliabilityRAG, a framework for adversarial robustness that explicitly leverages reliability information of retrieved documents. Our first contribution adopts a graph-theoretic perspective to identify a "consistent majority" among retrieved documents to filter out malicious ones. We introduce a novel algorithm based on finding a Maximum Independent Set (MIS) on a document graph where edges encode contradiction. Our MIS variant explicitly prioritizes higher-reliability documents and provides provable robustness guarantees against bounded adversarial corruption under natural assumptions. Recognizing the computational cost of exact MIS for large retrieval sets, our second contribution is a scalable weighted sample and aggregate framework. It explicitly utilizes reliability information, preserving some robustness guarantees while efficiently handling many documents. We present empirical results showing ReliabilityRAG provides superior robustness against adversarial attacks compared to prior methods, maintains high benign accuracy, and excels in long-form generation tasks where prior robustness-focused methods struggled. Our work is a significant step towards more effective, provably robust defenses against retrieved corpus corruption in RAG.

Humans can extract rich semantic information from minimal visual cues, as demonstrated by point-light displays (PLDs), which consist of sparse sets of dots localized to key joints of the human body. This ability emerges early in development and is largely attributed to human embodied experience. Since PLDs isolate body motion as the sole source of meaning, they represent key stimuli for testing the constraints of action understanding in these systems. Here we introduce ActPLD, the first benchmark to evaluate action processing in MLLMs from human PLDs. Tested models include state-of-the-art proprietary and open-source systems on single-actor and socially interacting PLDs. Our results reveal consistently low performance across models, introducing fundamental gaps in action and spatiotemporal understanding.

Natural language processing (NLP), particularly sentiment analysis, plays a vital role in areas like marketing, customer service, and social media monitoring by providing insights into user opinions and emotions. However, progress in Arabic sentiment analysis remains limited due to the lack of large, high-quality labeled datasets. While active learning has proven effective in reducing annotation efforts in other languages, few studies have explored it in Arabic sentiment tasks. Likewise, the use of large language models (LLMs) for assisting annotation and comparing their performance to human labeling is still largely unexplored in the Arabic context. In this paper, we propose an active learning framework for Arabic sentiment analysis designed to reduce annotation costs while maintaining high performance. We evaluate multiple deep learning architectures: Specifically, long short-term memory (LSTM), gated recurrent units (GRU), and recurrent neural networks (RNN), across three benchmark datasets: Hunger Station, AJGT, and MASAC, encompassing both modern standard Arabic and dialectal variations. Additionally, two annotation strategies are compared: Human labeling and LLM-assisted labeling. Five LLMs are evaluated as annotators: GPT-4o, Claude 3 Sonnet, Gemini 2.5 Pro, DeepSeek Chat, and LLaMA 3 70B Instruct. For each dataset, the best-performing LLM was used: GPT-4o for Hunger Station, Claude 3 Sonnet for AJGT, and DeepSeek Chat for MASAC. Our results show that LLM-assisted active learning achieves competitive or superior performance compared to human labeling. For example, on the Hunger Station dataset, the LSTM model achieved 93% accuracy with only 450 labeled samples using GPT-4o-generated labels, while on the MASAC dataset, DeepSeek Chat reached 82% accuracy with 650 labeled samples, matching the accuracy obtained through human labeling.