The training of controllable text-to-video (T2V) models relies heavily on the alignment between videos and captions, yet little existing research connects video caption evaluation with T2V generation assessment. This paper introduces VidCapBench, a video caption evaluation scheme specifically designed for T2V generation, agnostic to any particular caption format. VidCapBench employs a data annotation pipeline, combining expert model labeling and human refinement, to associate each collected video with key information spanning video aesthetics, content, motion, and physical laws. VidCapBench then partitions these key information attributes into automatically assessable and manually assessable subsets, catering to both the rapid evaluation needs of agile development and the accuracy requirements of thorough validation. By evaluating numerous state-of-the-art captioning models, we demonstrate the superior stability and comprehensiveness of VidCapBench compared to existing video captioning evaluation approaches. Verification with off-the-shelf T2V models reveals a significant positive correlation between scores on VidCapBench and the T2V quality evaluation metrics, indicating that VidCapBench can provide valuable guidance for training T2V models. The project is available at https://github.com/VidCapBench/VidCapBench.

Despite progress in Arabic large language models, such as Jais and AceGPT, their evaluation on commonsense reasoning has largely relied on machine-translated datasets, which lack cultural depth and may introduce Anglocentric biases. Commonsense reasoning is shaped by geographical and cultural contexts, and existing English datasets fail to capture the diversity of the Arab world. To address this, we introduce \datasetname, a commonsense reasoning dataset in Modern Standard Arabic (MSA), covering cultures of 13 countries across the Gulf, Levant, North Africa, and the Nile Valley. The dataset was built from scratch by engaging native speakers to write and validate culturally relevant questions for their respective countries. \datasetname spans 12 daily life domains with 54 fine-grained subtopics, reflecting various aspects of social norms, traditions, and everyday experiences. Zero-shot evaluations show that open-weight language models with up to 32B parameters struggle to comprehend diverse Arab cultures, with performance varying across regions. These findings highlight the need for more culturally aware models and datasets tailored to the Arabic-speaking world.

Current multimodal information retrieval studies mainly focus on single-image inputs, which limits real-world applications involving multiple images and text-image interleaved content. In this work, we introduce the text-image interleaved retrieval (TIIR) task, where the query and document are interleaved text-image sequences, and the model is required to understand the semantics from the interleaved context for effective retrieval. We construct a TIIR benchmark based on naturally interleaved wikiHow tutorials, where a specific pipeline is designed to generate interleaved queries. To explore the task, we adapt several off-the-shelf retrievers and build a dense baseline by interleaved multimodal large language model (MLLM). We then propose a novel Matryoshka Multimodal Embedder (MME), which compresses the number of visual tokens at different granularity, to address the challenge of excessive visual tokens in MLLM-based TIIR models. Experiments demonstrate that simple adaption of existing models does not consistently yield effective results. Our MME achieves significant improvements over the baseline by substantially fewer visual tokens. We provide extensive analysis and will release the dataset and code to facilitate future research.

In this study, we explore the application of Large Language Models (LLMs) for generating synthetic users and simulating user conversations with a task-oriented dialogue system and present detailed results and their analysis. We propose a comprehensive novel approach to user simulation technique that uses LLMs to create diverse user profiles, set goals, engage in multi-turn dialogues, and evaluate the conversation success. We employ two proprietary LLMs, namely GPT-4o and GPT-o1 (Achiam et al., 2023), to generate a heterogeneous base of user profiles, characterized by varied demographics, multiple user goals, different conversational styles, initial knowledge levels, interests, and conversational objectives. We perform a detailed analysis of the user profiles generated by LLMs to assess the diversity, consistency, and potential biases inherent in these LLM-generated user simulations. We find that GPT-o1 generates more heterogeneous user distribution across most user attributes, while GPT-4o generates more skewed user attributes. The generated set of user profiles are then utilized to simulate dialogue sessions by interacting with a task-oriented dialogue system.

Inverse tasks can uncover potential reasoning gaps as Large Language Models (LLMs) scale up. In this work, we explore the redefinition task, in which we assign alternative values to well-known physical constants and units of measure, prompting LLMs to respond accordingly. Our findings show that not only does model performance degrade with scale, but its false confidence also rises. Moreover, while factors such as prompting strategies or response formatting are influential, they do not preclude LLMs from anchoring to memorized values.

Despite having a population of twenty million, Kazakhstan's culture and language remain underrepresented in the field of natural language processing. Although large language models (LLMs) continue to advance worldwide, progress in Kazakh language has been limited, as seen in the scarcity of dedicated models and benchmark evaluations. To address this gap, we introduce KazMMLU, the first MMLU-style dataset specifically designed for Kazakh language. KazMMLU comprises 23,000 questions that cover various educational levels, including STEM, humanities, and social sciences, sourced from authentic educational materials and manually validated by native speakers and educators. The dataset includes 10,969 Kazakh questions and 12,031 Russian questions, reflecting Kazakhstan's bilingual education system and rich local context. Our evaluation of several state-of-the-art multilingual models (Llama-3.1, Qwen-2.5, GPT-4, and DeepSeek V3) demonstrates substantial room for improvement, as even the best-performing models struggle to achieve competitive performance in Kazakh and Russian. These findings underscore significant performance gaps compared to high-resource languages. We hope that our dataset will enable further research and development of Kazakh-centric LLMs. Data and code will be made available upon acceptance.

When humans acquire first language(s), they first In contrast, subword LMs of all sizes perform learn to recognize single words before understanding much worse in a syntax-independent lexical decision the grammatical processes governing them setting and only reach comparable accuracy (Tomasello, 1992; Behrens, 2021). This simple when stimuli are measured through surprisal, "unexpectedness" fact about language acquisition has found surprisingly in syntactic contexts. By comparing little attention in the increasing amount of word and syntactic learning (measured via BLiMP, work that treats LMs as models of language learners Warstadt et al., 2020), we further find that character (Warstadt and Bowman, 2022; Portelance and models quickly acquire lexical knowledge Jasbi, 2024). While word learning in children is and only later develop syntactic knowledge. In well studied, the implicit word learning processes subword models, however, word learning happens in LMs are not. Current studies overwhelmingly focus later and concurrently with syntax learning, bringing on syntax (Mueller et al., 2022; Choshen et al., further evidence against the cognitive plausibility 2022), or investigate word learning in close connection of subword tokenization. This shows how to syntax through surprisal (Chang and Bergen, elementary decisions (like choice of tokenization) 2022; Portelance et al., 2023; Shafiabadi and Wisniewski, can tremendously influence the learning dynamics 2025; Ficarra et al., 2025). Architecturewise, and trajectories that can be observed in LMs, a fact a key limitation to the precise study of word that should receive more scrutiny in studies of LMs learning is subword tokenization (e.g.

Large language models (LLMs) are revolutionizing healthcare by improving diagnosis, patient care, and decision support through interactive communication. More recently, they have been applied to analyzing physiological time-series like wearable data for health insight extraction. Existing methods embed raw numerical sequences directly into prompts, which exceeds token limits and increases computational costs. Additionally, some studies integrated features extracted from time-series in textual prompts or applied multimodal approaches. However, these methods often produce generic and unreliable outputs due to LLMs' limited analytical rigor and inefficiency in interpreting continuous waveforms. In this paper, we develop an LLM-powered agent for physiological time-series analysis aimed to bridge the gap in integrating LLMs with well-established analytical tools. Built on the OpenCHA, an open-source LLM-powered framework, our agent features an orchestrator that integrates user interaction, data sources, and analytical tools to generate accurate health insights. To evaluate its effectiveness, we implement a case study on heart rate (HR) estimation from Photoplethysmogram (PPG) signals using a dataset of PPG and Electrocardiogram (ECG) recordings in a remote health monitoring study. The agent's performance is benchmarked against OpenAI GPT-4o-mini and GPT-4o, with ECG serving as the gold standard for HR estimation. Results demonstrate that our agent significantly outperforms benchmark models by achieving lower error rates and more reliable HR estimations. The agent implementation is publicly available on GitHub.

The recent advances in large language models (LLMs) have revolutionized industries such as finance, marketing, and customer service by enabling sophisticated natural language processing tasks. However, the broad adoption of LLMs brings significant challenges, particularly in the form of social biases that can be embedded within their outputs. Biases related to gender, age, and other sensitive attributes can lead to unfair treatment, raising ethical concerns and risking both company reputation and customer trust. This study examined bias in finance-related marketing slogans generated by LLMs (i.e., ChatGPT) by prompting tailored ads targeting five demographic categories: gender, marital status, age, income level, and education level. A total of 1,700 slogans were generated for 17 unique demographic groups, and key terms were categorized into four thematic groups: empowerment, financial, benefits and features, and personalization. Bias was systematically assessed using relative bias calculations and statistically tested with the Kolmogorov-Smirnov (KS) test against general slogans generated for any individual. Results revealed that marketing slogans are not neutral; rather, they emphasize different themes based on demographic factors. Women, younger individuals, low-income earners, and those with lower education levels receive more distinct messaging compared to older, higher-income, and highly educated individuals. This underscores the need to consider demographic-based biases in AI-generated marketing strategies and their broader societal implications. The findings of this study provide a roadmap for developing more equitable AI systems, highlighting the need for ongoing bias detection and mitigation efforts in LLMs.

Effective feedback is essential for fostering students' success in scientific inquiry. With advancements in artificial intelligence, large language models (LLMs) offer new possibilities for delivering instant and adaptive feedback. However, this feedback often lacks the pedagogical validation provided by real-world practitioners. To address this limitation, our study evaluates and compares the feedback quality of LLM agents with that of human teachers and science education experts on student-written experimentation protocols. Four blinded raters, all professionals in scientific inquiry and science education, evaluated the feedback texts generated by 1) the LLM agent, 2) the teachers and 3) the science education experts using a five-point Likert scale based on six criteria of effective feedback: Feed Up, Feed Back, Feed Forward, Constructive Tone, Linguistic Clarity, and Technical Terminology. Our results indicate that LLM-generated feedback shows no significant difference to that of teachers and experts in overall quality. However, the LLM agent's performance lags in the Feed Back dimension, which involves identifying and explaining errors within the student's work context. Qualitative analysis highlighted the LLM agent's limitations in contextual understanding and in the clear communication of specific errors. Our findings suggest that combining LLM-generated feedback with human expertise can enhance educational practices by leveraging the efficiency of LLMs and the nuanced understanding of educators.