The proliferation of disinformation presents a growing threat to societal trust and democracy, necessitating robust and scalable Fact-Checking systems. In this work, we present Dynamic Evidence-based FAct-checking with Multimodal Experts (DEFAME), a modular, zero-shot MLLM pipeline for open-domain, text-image claim verification. DEFAME frames the problem of fact-checking as a six-stage process, dynamically deciding about the usage of external tools for the retrieval of textual and visual evidence. In addition to the claim's veracity, DEFAME returns a justification accompanied by a comprehensive, multimodal fact-checking report. While most alternatives either focus on sub-tasks of fact-checking, lack explainability or are limited to text-only inputs, DEFAME solves the problem of fact-checking end-to-end, including claims with images or those that require visual evidence. Evaluation on the popular benchmarks VERITE, AVeriTeC, and MOCHEG shows that DEFAME surpasses all previous methods, establishing it as the new state-of-the-art fact-checking system.

Identifying salts from images of their'stains' has diverse practical applications. While specialized AI models are being developed, this paper explores the potential of OpenAI's state-of-the-art vision models (GPT-4o and GPT-4o-mini) as an immediate solution. Testing with 12 different types of salts, the GPT-4o model achieved 57% accuracy and a 0.52 F1 score, significantly outperforming both random chance (8%) and GPT-4o mini (11% accuracy). However, GPT-4o mini also had significantly biased responses, diminishing the representativeness of its accuracy. Results suggest that current vision models could serve as an interim solution for salt identification from their stain images.

Despite the rapid advancements in language and image-language modeling (Hoffmann et al., 2022; Brown, 2020; Yang et al., 2024; Liu et al., 2024a; Alayrac et al., 2022; Laurençon et al., 2024a; OpenAI, 2024), the development of video Large Multimodal Models (video-LMMs) has not kept pace. Videos provide a rich, dynamic information source, capturing nuanced temporal and spatial features beyond the reach of static images. However, video-LMMs remain under-explored, hampered by unique challenges: notably higher computational demands and a broader, more complex design space compared to their image-based counterparts (Li et al., 2023a, 2025; Liu et al., 2024d; Li et al., 2024b; Xu et al., 2024a). Many fundamental questions about video-LMM design remain unanswered: How should videos be sampled? Which vision encoders yield optimal representations? What are the best practices for resampling video tokens? Early approaches primarily extended image-LMMs directly (Xu et al., 2024b; Kim et al., 2024; Wu, 2024; Zhang et al., 2024e) or with video-specific fine-tuning (Li et al., 2023a; Zhang et al., 2023; Maaz et al., 2023). Recent methods introduced diverse design choices, such as longer context windows (Zhang et al., 2024e), multi-modality mixing (Li et al., 2024a,c), agent workflows (Wang et al., 2024c), self-training (Zohar et al., 2024), and more. Despite these efforts, the impact of these design decisions on video-LMM performance is poorly understood.

LLMs can generate human-like dialogues, yet their ability to simulate early child-adult interactions remains largely unexplored. In this paper, we examined how effectively LLMs can capture the distinctive features of child-caregiver language in interaction, using both static and interactive benchmarking methods. We found that state-of-the-art LLMs like Llama 3 and GPT-4o can approximate child-caregiver dialogues at the word and utterance level, but they struggle to reproduce the child and caregiver's discursive patterns, exaggerate alignment, and fail to reach the level of diversity shown by humans. The broader goal of this work is to initiate the development of a comprehensive benchmark for LLMs in child-oriented applications.

The development and evaluation of Large Language Models (LLMs) has primarily focused on their task-solving capabilities, with recent models even surpassing human performance in some areas. However, this focus often neglects whether machine-generated language matches the human level of diversity, in terms of vocabulary choice, syntactic construction, and expression of meaning, raising questions about whether the fundamentals of language generation have been fully addressed. This paper emphasizes the importance of examining the preservation of human linguistic richness by language models, given the concerning surge in online content produced or aided by LLMs. We propose a comprehensive framework for evaluating LLMs from various linguistic diversity perspectives including lexical, syntactic, and semantic dimensions. Using this framework, we benchmark several state-of-the-art LLMs across all diversity dimensions, and conduct an in-depth case study for syntactic diversity. Finally, we analyze how different development and deployment choices impact the linguistic diversity of LLM outputs.

In this work we introduce an open-ended question benchmark, ALDbench, to evaluate the performance of large language models (LLMs) in materials synthesis, and in particular in the field of atomic layer deposition, a thin film growth technique used in energy applications and microelectronics. Our benchmark comprises questions with a level of difficulty ranging from graduate level to domain expert current with the state of the art in the field. Human experts reviewed the questions along the criteria of difficulty and specificity, and the model responses along four different criteria: overall quality, specificity, relevance, and accuracy. We ran this benchmark on an instance of OpenAI's GPT-4o. The responses from the model received a composite quality score of 3.7 on a 1 to 5 scale, consistent with a passing grade. However, 36% of the questions received at least one below average score. An in-depth analysis of the responses identified at least five instances of suspected hallucination. Finally, we observed statistically significant correlations between the difficulty of the question and the quality of the response, the difficulty of the question and the relevance of the response, and the specificity of the question and the accuracy of the response as graded by the human experts. This emphasizes the need to evaluate LLMs across multiple criteria beyond difficulty or accuracy.

Advanced applied mathematics problems are underrepresented in existing Large Language Model (LLM) benchmark datasets. To address this, we introduce HARDMath, a dataset inspired by a graduate course on asymptotic methods, featuring challenging applied mathematics problems that require analytical approximation techniques. These problems demand a combination of mathematical reasoning, computational tools, and subjective judgment, making them difficult for LLMs. Our framework auto-generates a large number of problems with solutions validated against numerical ground truths. We evaluate both open- and closed-source LLMs on HARDMath-mini, a sub-sampled test set of 366 problems, as well as on 40 word problems formulated in applied science contexts. Even leading closed-source models like GPT-4 achieve only 43.8% overall accuracy with few-shot Chain-of-Thought prompting, and all models demonstrate significantly lower performance compared to results on existing mathematics benchmark datasets. We additionally conduct a detailed error analysis to gain insights into the failure cases of LLMs. These results demonstrate limitations of current LLM performance on advanced graduate-level applied math problems and underscore the importance of datasets like HARDMath to advance mathematical abilities of LLMs.

This paper introduces the human-like embodied AI interviewer which integrates android robots equipped with advanced conversational capabilities, including attentive listening, conversational repairs, and user fluency adaptation. Moreover, it can analyze and present results post-interview. We conducted a real-world case study at SIGDIAL 2024 with 42 participants, of whom 69% reported positive experiences. This study demonstrated the system's effectiveness in conducting interviews just like a human and marked the first employment of such a system at an international conference. The demonstration video is available at https://youtu.be/jCuw9g99KuE.

Language models (LMs) have excelled in various broad domains. However, to ensure their safe and effective integration into real-world educational settings, they must demonstrate proficiency in specific, granular areas of knowledge. Existing cloze-style benchmarks, commonly used to evaluate LMs' knowledge, have three major limitations. They: 1) do not cover the educational domain; 2) typically focus on low-complexity, generic knowledge or broad domains, which do not adequately assess the models' knowledge in specific subjects; and 3) often rely on templates that can bias model predictions. Here, we introduce MALAMUTE, a multilingual, template-free, and highly granular probing dataset comprising expert-written, peer-reviewed probes from 71 university-level textbooks across three languages (English, Spanish, and Polish). MALAMUTE is the first education-based cloze-style dataset. It covers eight domains, each with up to 14 subdomains, further broken down into concepts and concept-based prompts, totaling 33,361 university curriculum concepts and 116,887 prompts. MALAMUTE's fine granularity, educational focus, and inclusion of both sentence-level and paragraph-level prompts make it an ideal tool for evaluating LMs' course-related knowledge. Our evaluation of masked and causal LMs on MALAMUTE shows that despite overall proficiency, they have significant gaps in knowledge when examined closely on specific subjects, hindering their safe use in classrooms and underscoring the need for further development.

Research and industry are rapidly advancing the innovation and adoption of foundation model-based systems, yet the tools for managing these models have not kept pace. Understanding the provenance and lineage of models is critical for researchers, industry, regulators, and public trust. While model cards and system cards were designed to provide transparency, they fall short in key areas: tracing model genealogy, enabling machine readability, offering reliable centralized management systems, and fostering consistent creation incentives. This challenge mirrors issues in software supply chain security, but AI/ML remains at an earlier stage of maturity. Addressing these gaps requires industry-standard tooling that can be adopted by foundation model publishers, open-source model innovators, and major distribution platforms. We propose a machine-readable model specification format to simplify the creation of model records, thereby reducing error-prone human effort, notably when a new model inherits most of its design from a foundation model. Our solution explicitly traces relationships between upstream and downstream models, enhancing transparency and traceability across the model lifecycle. To facilitate the adoption, we introduce the unified model record (UMR) repository , a semantically versioned system that automates the publication of model records to multiple formats (PDF, HTML, LaTeX) and provides a hosted web interface (https://modelrecord.com/). This proof of concept aims to set a new standard for managing foundation models, bridging the gap between innovation and responsible model management.