Multilingual Performance Biases of Large Language Models in Education

Large language models (LLMs) are increasingly being adopted in educational settings. These applications expand beyond English, though current LLMs remain primarily English-centric. In this work, we ascertain if their use in education settings in non-English languages is warranted. We evaluated the performance of popular LLMs on four educational tasks: identifying student misconceptions, providing targeted feedback, interactive tutoring, and grading translations in six languages (Hindi, Arabic, Farsi, Telugu, Ukrainian, Czech) in addition to English. We find that the performance on these tasks somewhat corresponds to the amount of language represented in training data, with lower-resource languages having poorer task performance. Although the models perform reasonably well in most languages, the frequent performance drop from English is significant. Thus, we recommend that practitioners first verify that the LLM works well in the target language for their educational task before deployment.

Quadratic Interest Network for Multimodal Click-Through Rate Prediction

Multimodal click-through rate (CTR) prediction is a key technique in industrial recommender systems. It leverages heterogeneous modalities such as text, images, and behavioral logs to capture high-order feature interactions between users and items, thereby enhancing the system's understanding of user interests and its ability to predict click behavior. The primary challenge in this field lies in effectively utilizing the rich semantic information from multiple modalities while satisfying the low-latency requirements of online inference in real-world applications. To foster progress in this area, the Multimodal CTR Prediction Challenge Track of the WWW 2025 EReL@MIR Workshop formulates the problem into two tasks: (1) Task 1 of Multimodal Item Embedding: this task aims to explore multimodal information extraction and item representation learning methods that enhance recommendation tasks; and (2) Task 2 of Multimodal CTR Prediction: this task aims to explore what multimodal recommendation model can effectively leverage multimodal embedding features and achieve better performance. In this paper, we propose a novel model for Task 2, named Quadratic Interest Network (QIN) for Multimodal CTR Prediction. Specifically, QIN employs adaptive sparse target attention to extract multimodal user behavior features, and leverages Quadratic Neural Networks to capture high-order feature interactions. As a result, QIN achieved an AUC of 0.9798 on the leaderboard and ranked second in the competition. The model code, training logs, hyperparameter configurations, and checkpoints are available at https://github.com/salmon1802/QIN.

IRA: Adaptive Interest-aware Representation and Alignment for Personalized Multi-interest Retrieval

Online community platforms require dynamic personalized retrieval and recommendation that can continuously adapt to evolving user interests and new documents. However, optimizing models to handle such changes in real-time remains a major challenge in large-scale industrial settings. To address this, we propose the Interest-aware Representation and Alignment (IRA) framework, an efficient and scalable approach that dynamically adapts to new interactions through a cumulative structure. IRA leverages two key mechanisms: (1) Interest Units that capture diverse user interests as contextual texts, while reinforcing or fading over time through cumulative updates, and (2) a retrieval process that measures the relevance between Interest Units and documents based solely on semantic relationships, eliminating dependence on click signals to mitigate temporal biases. By integrating cumulative Interest Unit updates with the retrieval process, IRA continuously adapts to evolving user preferences, ensuring robust and fine-grained personalization without being constrained by past training distributions. We validate the effectiveness of IRA through extensive experiments on real-world datasets, including its deployment in the Home Section of NAVER's CAFE, South Korea's leading community platform.

Beyond Whole Dialogue Modeling: Contextual Disentanglement for Conversational Recommendation

Conversational recommender systems aim to provide personalized recommendations by analyzing and utilizing contextual information related to dialogue. However, existing methods typically model the dialogue context as a whole, neglecting the inherent complexity and entanglement within the dialogue. Specifically, a dialogue comprises both focus information and background information, which mutually influence each other. Current methods tend to model these two types of information mixedly, leading to misinterpretation of users' actual needs, thereby lowering the accuracy of recommendations. To address this issue, this paper proposes a novel model to introduce contextual disentanglement for improving conversational recommender systems, named DisenCRS. The proposed model DisenCRS employs a dual disentanglement framework, including self-supervised contrastive disentanglement and counterfactual inference disentanglement, to effectively distinguish focus information and background information from the dialogue context under unsupervised conditions. Moreover, we design an adaptive prompt learning module to automatically select the most suitable prompt based on the specific dialogue context, fully leveraging the power of large language models. Experimental results on two widely used public datasets demonstrate that DisenCRS significantly outperforms existing conversational recommendation models, achieving superior performance on both item recommendation and response generation tasks.

You Are What You Bought: Generating Customer Personas for E-commerce Applications

In e-commerce, user representations are essential for various applications. Existing methods often use deep learning techniques to convert customer behaviors into implicit embeddings. However, these embeddings are difficult to understand and integrate with external knowledge, limiting the effectiveness of applications such as customer segmentation, search navigation, and product recommendations. To address this, our paper introduces the concept of the customer persona. Condensed from a customer's numerous purchasing histories, a customer persona provides a multi-faceted and human-readable characterization of specific purchase behaviors and preferences, such as Busy Parents or Bargain Hunters. This work then focuses on representing each customer by multiple personas from a predefined set, achieving readable and informative explicit user representations. To this end, we propose an effective and efficient solution GPLR. To ensure effectiveness, GPLR leverages pre-trained LLMs to infer personas for customers. To reduce overhead, GPLR applies LLM-based labeling to only a fraction of users and utilizes a random walk technique to predict personas for the remaining customers. We further propose RevAff, which provides an absolute error $\epsilon$ guarantee while improving the time complexity of the exact solution by a factor of at least $O(\frac{\epsilon\cdot|E|N}{|E|+N\log N})$, where $N$ represents the number of customers and products, and $E$ represents the interactions between them. We evaluate the performance of our persona-based representation in terms of accuracy and robustness for recommendation and customer segmentation tasks using three real-world e-commerce datasets. Most notably, we find that integrating customer persona representations improves the state-of-the-art graph convolution-based recommendation model by up to 12% in terms of NDCG@K and F1-Score@K.

Fine-tune Smarter, Not Harder: Parameter-Efficient Fine-Tuning for Geospatial Foundation Models

Earth observation (EO) is crucial for monitoring environmental changes, responding to disasters, and managing natural resources. In this context, foundation models facilitate remote sensing image analysis to retrieve relevant geoinformation accurately and efficiently. However, as these models grow in size, fine-tuning becomes increasingly challenging due to the associated computational resources and costs, limiting their accessibility and scalability. Furthermore, full fine-tuning can lead to forgetting pre-trained features and even degrade model generalization. To address this, Parameter-Efficient Fine-Tuning (PEFT) techniques offer a promising solution. In this paper, we conduct extensive experiments with various foundation model architectures and PEFT techniques to evaluate their effectiveness on five different EO datasets. Our results provide a comprehensive comparison, offering insights into when and how PEFT methods support the adaptation of pre-trained geospatial models. We demonstrate that PEFT techniques match or even exceed full fine-tuning performance and enhance model generalisation to unseen geographic regions, while reducing training time and memory requirements. Additional experiments investigate the effect of architecture choices such as the decoder type or the use of metadata, suggesting UNet decoders and fine-tuning without metadata as the recommended configuration. We have integrated all evaluated foundation models and techniques into the open-source package TerraTorch to support quick, scalable, and cost-effective model adaptation.

Agree to Disagree? A Meta-Evaluation of LLM Misgendering

Numerous methods have been proposed to measure LLM misgendering, including probability-based evaluations (e.g., automatically with templatic sentences) and generation-based evaluations (e.g., with automatic heuristics or human validation). However, it has gone unexamined whether these evaluation methods have convergent validity, that is, whether their results align. Therefore, we conduct a systematic meta-evaluation of these methods across three existing datasets for LLM misgendering. We propose a method to transform each dataset to enable parallel probability- and generation-based evaluation. Then, by automatically evaluating a suite of 6 models from 3 families, we find that these methods can disagree with each other at the instance, dataset, and model levels, conflicting on 20.2% of evaluation instances. Finally, with a human evaluation of 2400 LLM generations, we show that misgendering behaviour is complex and goes far beyond pronouns, which automatic evaluations are not currently designed to capture, suggesting essential disagreement with human evaluations. Based on our findings, we provide recommendations for future evaluations of LLM misgendering. Our results are also more widely relevant, as they call into question broader methodological conventions in LLM evaluation, which often assume that different evaluation methods agree.

Approaches to Responsible Governance of GenAI in Organizations

The rapid evolution of Generative AI (GenAI) has introduced unprecedented opportunities while presenting complex challenges around ethics, accountability, and societal impact. This paper draws on a literature review, established governance frameworks, and industry roundtable discussions to identify core principles for integrating responsible GenAI governance into diverse organizational structures. Our objective is to provide actionable recommendations for a balanced, risk-based governance approach that enables both innovation and oversight. Findings emphasize the need for adaptable risk assessment tools, continuous monitoring practices, and cross-sector collaboration to establish trustworthy GenAI. These insights provide a structured foundation and Responsible GenAI Guide (ResAI) for organizations to align GenAI initiatives with ethical, legal, and operational best practices.

Building A Secure Agentic AI Application Leveraging A2A Protocol

As Agentic AI systems evolve from basic workflows to complex multi agent collaboration, robust protocols such as Google's Agent2Agent (A2A) become essential enablers. To foster secure adoption and ensure the reliability of these complex interactions, understanding the secure implementation of A2A is essential. This paper addresses this goal by providing a comprehensive security analysis centered on the A2A protocol. We examine its fundamental elements and operational dynamics, situating it within the framework of agent communication development. Utilizing the MAESTRO framework, specifically designed for AI risks, we apply proactive threat modeling to assess potential security issues in A2A deployments, focusing on aspects such as Agent Card management, task execution integrity, and authentication methodologies. Based on these insights, we recommend practical secure development methodologies and architectural best practices designed to build resilient and effective A2A systems. Our analysis also explores how the synergy between A2A and the Model Context Protocol (MCP) can further enhance secure interoperability. This paper equips developers and architects with the knowledge and practical guidance needed to confidently leverage the A2A protocol for building robust and secure next generation agentic applications.

Evaluation Framework for AI Systems in "the Wild"

Generative AI (GenAI) models have become vital across industries, yet current evaluation methods have not adapted to their widespread use. Traditional evaluations often rely on benchmarks and fixed datasets, frequently failing to reflect real-world performance, which creates a gap between lab-tested outcomes and practical applications. This white paper proposes a comprehensive framework for how we should evaluate real-world GenAI systems, emphasizing diverse, evolving inputs and holistic, dynamic, and ongoing assessment approaches. The paper offers guidance for practitioners on how to design evaluation methods that accurately reflect real-time capabilities, and provides policymakers with recommendations for crafting GenAI policies focused on societal impacts, rather than fixed performance numbers or parameter sizes. We advocate for holistic frameworks that integrate performance, fairness, and ethics and the use of continuous, outcome-oriented methods that combine human and automated assessments while also being transparent to foster trust among stakeholders. Implementing these strategies ensures GenAI models are not only technically proficient but also ethically responsible and impactful.