Black-Box prompt optimization methods have emerged as a promising strategy for refining input prompts to better align large language models (LLMs), thereby enhancing their task performance. Although these methods have demonstrated encouraging results, most studies and experiments have primarily focused on smaller-scale models (e.g., 7B, 14B) or earlier versions (e.g., GPT-3.5) of LLMs. As the scale of LLMs continues to increase, such as with DeepSeek V3 (671B), it remains an open question whether these black-box optimization techniques will continue to yield significant performance improvements for models of such scale. In response to this, we select three well-known black-box optimization methods and evaluate them on large-scale LLMs (DeepSeek V3 and Gemini 2.0 Flash) across four NLU and NLG datasets. The results show that these black-box prompt optimization methods offer only limited improvements on these large-scale LLMs. Furthermore, we hypothesize that the scale of the model is the primary factor contributing to the limited benefits observed. To explore this hypothesis, we conducted experiments on LLMs of varying sizes (Qwen 2.5 series, ranging from 7B to 72B) and observed an inverse scaling law, wherein the effectiveness of black-box optimization methods diminished as the model size increased.

Over the past three years, the rapid advancement of Large Language Models (LLMs) has had a profound impact on multiple areas of Artificial Intelligence (AI), particularly in Natural Language Processing (NLP) across diverse languages, including Arabic. Although Arabic is considered one of the most widely spoken languages across 27 countries in the Arabic world and used as a second language in some other non-Arabic countries as well, there is still a scarcity of Arabic resources, datasets, and tools. Arabic NLP tasks face various challenges due to the complexities of the Arabic language, including its rich morphology, intricate structure, and diverse writing standards, among other factors. Researchers have been actively addressing these challenges, demonstrating that pre-trained Large Language Models (LLMs) trained on multilingual corpora achieve significant success in various Arabic NLP tasks. This study provides an overview of using large language models (LLMs) for the Arabic language, highlighting early pre-trained Arabic Language models across various NLP applications and their ability to handle diverse Arabic content tasks and dialects. It also provides an overview of how techniques like finetuning and prompt engineering can enhance the performance of these models. Additionally, the study summarizes common Arabic benchmarks and datasets while presenting our observations on the persistent upward trend in the adoption of LLMs.

The rise of Large Language Models~(LLMs) revolutionizes information retrieval, allowing users to obtain required answers through complex instructions within conversations. However, publicly available services remain inadequate in addressing the needs of faculty and students to search campus-specific information. It is primarily due to the LLM's lack of domain-specific knowledge and the limitation of search engines in supporting multilingual and timely scenarios. To tackle these challenges, we introduce ALOHA, a multilingual agent enhanced by hierarchical retrieval for university orientation. We also integrate external APIs into the front-end interface to provide interactive service. The human evaluation and case study show our proposed system has strong capabilities to yield correct, timely, and user-friendly responses to the queries in multiple languages, surpassing commercial chatbots and search engines. The system has been deployed and has provided service for more than 12,000 people.

Topic modeling in Italian legal research is hindered by the lack of public datasets, limiting the analysis of legal themes in Supreme Court judgments. To address this, we developed a document processing pipeline that produces an anonymized dataset optimized for topic modeling. The pipeline integrates document layout analysis (YOLOv8x), optical character recognition, and text anonymization. The DLA module achieved a mAP@50 of 0.964 and a mAP@50-95 of 0.800. The OCR detector reached a mAP@50-95 of 0.9022, and the text recognizer (TrOCR) obtained a character error rate of 0.0047 and a word error rate of 0.0248. Compared to OCR-only methods, our dataset improved topic modeling with a diversity score of 0.6198 and a coherence score of 0.6638. We applied BERTopic to extract topics and used large language models to generate labels and summaries. Outputs were evaluated against domain expert interpretations. Claude Sonnet 3.7 achieved a BERTScore F1 of 0.8119 for labeling and 0.9130 for summarization.

The rapid development of large language models (LLMs) has transformed the landscape of natural language processing. Evaluating LLMs properly is crucial for understanding their potential and addressing concerns such as safety. However, LLM evaluation is confronted by various factors, among which contamination stands out as a key issue that undermines the reliability of evaluations. In this work, we introduce the concept of contamination resistance to address this challenge. We propose a benchmark based on Caesar ciphers (e.g., "ab" to "bc" when the shift is 1), which, despite its simplicity, is an excellent example of a contamination resistant benchmark. We test this benchmark on widely used LLMs under various settings, and we find that these models struggle with this benchmark when contamination is controlled. Our findings reveal issues in current LLMs and raise important questions regarding their true capabilities. Our work contributes to the development of contamination resistant benchmarks, enabling more rigorous LLM evaluation and offering insights into the true capabilities and limitations of LLMs.

Classroom discourse is an essential vehicle through which teaching and learning take place. Assessing different characteristics of discursive practices and linking them to student learning achievement enhances the understanding of teaching quality. Traditional assessments rely on manual coding of classroom observation protocols, which is time-consuming and costly. Despite many studies utilizing AI techniques to analyze classroom discourse at the utterance level, investigations into the evaluation of discursive practices throughout an entire lesson segment remain limited. To address this gap, our study proposes a novel text-centered multimodal fusion architecture to assess the quality of three discourse components grounded in the Global Teaching InSights (GTI) observation protocol: Nature of Discourse, Questioning, and Explanations. First, we employ attention mechanisms to capture inter- and intra-modal interactions from transcript, audio, and video streams. Second, a multi-task learning approach is adopted to jointly predict the quality scores of the three components. Third, we formulate the task as an ordinal classification problem to account for rating level order. The effectiveness of these designed elements is demonstrated through an ablation study on the GTI Germany dataset containing 92 videotaped math lessons. Our results highlight the dominant role of text modality in approaching this task. Integrating acoustic features enhances the model's consistency with human ratings, achieving an overall Quadratic Weighted Kappa score of 0.384, comparable to human inter-rater reliability (0.326). Our study lays the groundwork for the future development of automated discourse quality assessment to support teacher professional development through timely feedback on multidimensional discourse practices.

We study the post-training of large language models (LLMs) with human preference data. Recently, direct preference optimization and its variants have shown considerable promise in aligning language models, eliminating the need for reward models and online sampling. Despite these benefits, these methods rely on explicit assumptions about the Bradley-Terry (BT) model, which makes them prone to overfitting and results in suboptimal performance, particularly on reasoning-heavy tasks. To address these challenges, we propose a principled preference fine-tuning algorithm called InfoPO, which effectively and efficiently aligns large language models using preference data. InfoPO eliminates the reliance on the BT model and prevents the likelihood of the chosen response from decreasing. Extensive experiments confirm that InfoPO consistently outperforms established baselines on widely used open benchmarks, particularly in reasoning tasks.

Analyzing how the publication records of scientists and research groups have evolved over the years is crucial for assessing their expertise since it can support the management of academic environments by assisting with career planning and evaluation. We introduce VizCV, a novel web-based end-to-end visual analytics framework that enables the interactive exploration of researchers' scientific trajectories. It incorporates AI-assisted analysis and supports automated reporting of career evolution. Our system aims to model career progression through three key dimensions: a) research topic evolution to detect and visualize shifts in scholarly focus over time, b) publication record and the corresponding impact, c) collaboration dynamics depicting the growth and transformation of a researcher's co-authorship network. AI-driven insights provide automated explanations of career transitions, detecting significant shifts in research direction, impact surges, or collaboration expansions. The system also supports comparative analysis between researchers, allowing users to compare topic trajectories and impact growth. Our interactive, multi-tab and multiview system allows for the exploratory analysis of career milestones under different perspectives, such as the most impactful articles, emerging research themes, or obtaining a detailed analysis of the contribution of the researcher in a subfield. The key contributions include AI/ML techniques for: a) topic analysis, b) dimensionality reduction for visualizing patterns and trends, c) the interactive creation of textual descriptions of facets of data through configurable prompt generation and large language models, that include key indicators, to help understanding the career development of individuals or groups.

We explore the use of inner speech as a mechanism to enhance transparency and trust in social robots for dietary advice. In humans, inner speech structures thought processes and decision-making; in robotics, it improves explainability by making reasoning explicit. This is crucial in healthcare scenarios, where trust in robotic assistants depends on both accurate recommendations and human-like dialogue, which make interactions more natural and engaging. Building on this, we developed a social robot that provides dietary advice, and we provided the architecture with inner speech capabilities to validate user input, refine reasoning, and generate clear justifications. The system integrates large language models for natural language understanding and a knowledge graph for structured dietary information. By making decisions more transparent, our approach strengthens trust and improves human-robot interaction in healthcare. We validated this by measuring the computational efficiency of our architecture and conducting a small user study, which assessed the reliability of inner speech in explaining the robot's behavior.

Large language models (LLMs) hosted on cloud servers alleviate the computational and storage burdens on local devices but raise privacy concerns due to sensitive data transmission and require substantial communication bandwidth, which is challenging in constrained environments. In contrast, small language models (SLMs) running locally enhance privacy but suffer from limited performance on complex tasks. To balance computational cost, performance, and privacy protection under bandwidth constraints, we propose a privacy-aware wireless collaborative mixture of experts (PWC-MoE) framework. Specifically, PWC-MoE employs a sparse privacy-aware gating network to dynamically route sensitive tokens to privacy experts located on local clients, while non-sensitive tokens are routed to non-privacy experts located at the remote base station. To achieve computational efficiency, the gating network ensures that each token is dynamically routed to and processed by only one expert. To enhance scalability and prevent overloading of specific experts, we introduce a group-wise load-balancing mechanism for the gating network that evenly distributes sensitive tokens among privacy experts and non-sensitive tokens among non-privacy experts. To adapt to bandwidth constraints while preserving model performance, we propose a bandwidth-adaptive and importance-aware token offloading scheme. This scheme incorporates an importance predictor to evaluate the importance scores of non-sensitive tokens, prioritizing the most important tokens for transmission to the base station based on their predicted importance and the available bandwidth. Experiments demonstrate that the PWC-MoE framework effectively preserves privacy and maintains high performance even in bandwidth-constrained environments, offering a practical solution for deploying LLMs in privacy-sensitive and bandwidth-limited scenarios.