Large language models (LLMs) exhibit advancing capabilities in complex tasks, such as reasoning and graduate-level question answering, yet their resilience against misuse, particularly involving scientifically sophisticated risks, remains underexplored. Existing safety benchmarks typically focus either on instructions requiring minimal knowledge comprehension (e.g., ``tell me how to build a bomb") or utilize prompts that are relatively low-risk (e.g., multiple-choice or classification tasks about hazardous content). Consequently, they fail to adequately assess model safety when handling knowledge-intensive, hazardous scenarios. To address this critical gap, we introduce SOSBench, a regulation-grounded, hazard-focused benchmark encompassing six high-risk scientific domains: chemistry, biology, medicine, pharmacology, physics, and psychology. The benchmark comprises 3,000 prompts derived from real-world regulations and laws, systematically expanded via an LLM-assisted evolutionary pipeline that introduces diverse, realistic misuse scenarios (e.g., detailed explosive synthesis instructions involving advanced chemical formulas). We evaluate frontier models within a unified evaluation framework using our SOSBench. Despite their alignment claims, advanced models consistently disclose policy-violating content across all domains, demonstrating alarmingly high rates of harmful responses (e.g., 79.1% for Deepseek-R1 and 47.3% for GPT-4.1). These results highlight significant safety alignment deficiencies and underscore urgent concerns regarding the responsible deployment of powerful LLMs.
In this short report, we present an automated pipeline tailored for the genomics domain and introduce \textit{Genome-Bench}, a new benchmark constructed from over a decade of scientific forum discussions on genome engineering. Our pipeline transforms raw interactions into a reinforcement learning friendly multiple-choice questions format, supported by 3000+ high quality question answer pairs spanning foundational biology, experimental troubleshooting, tool usage, and beyond. To our knowledge, this is the first end-to-end pipeline for teaching LLMs to reason from scientific discussions, with promising potential for generalization across scientific domains beyond biology.
Existing large language models (LLMs) driven search agents typically rely on prompt engineering to decouple the user queries into search plans, limiting their effectiveness in complex scenarios requiring reasoning. Furthermore, they suffer from excessive token consumption due to Python-based search plan representations and inadequate integration of multimedia elements for both input processing and response generation. To address these challenges, we introduce SearchExpert, a training method for LLMs to improve their multimedia search capabilities in response to complex search queries. Firstly, we reformulate the search plan in an efficient natural language representation to reduce token consumption. Then, we propose the supervised fine-tuning for searching (SFTS) to fine-tune LLM to adapt to these representations, together with an automated dataset construction pipeline. Secondly, to improve reasoning-intensive search capabilities, we propose the reinforcement learning from search feedback (RLSF) that takes the search results planned by LLM as the reward signals. Thirdly, we propose a multimedia understanding and generation agent that enables the fine-tuned LLM to process visual input and produce visual output during inference. Finally, we establish an automated benchmark construction pipeline and a human evaluation framework. Our resulting benchmark, SearchExpertBench-25, comprises 200 multiple-choice questions spanning financial and international news scenarios that require reasoning in searching. Experiments demonstrate that SearchExpert outperforms the commercial LLM search method (Perplexity Pro) by 36.60% on the existing FinSearchBench-24 benchmark and 54.54% on our proposed SearchExpertBench-25. Human evaluations further confirm the superior readability.
Recent advances in Large Reasoning Models (LRMs) have significantly improved long-chain reasoning capabilities over Large Language Models (LLMs). However, LRMs often produce unnecessarily lengthy outputs even for simple queries, leading to inefficiencies or even accuracy degradation compared to LLMs. To overcome this, we propose CP-Router, a training-free and model-agnostic routing framework that dynamically selects between an LLM and an LRM, demonstrated with multiple-choice question answering (MCQA) prompts. The routing decision is guided by the prediction uncertainty estimates derived via Conformal Prediction (CP), which provides rigorous coverage guarantees. To further refine the uncertainty differentiation across inputs, we introduce Full and Binary Entropy (FBE), a novel entropy-based criterion that adaptively selects the appropriate CP threshold. Experiments across diverse MCQA benchmarks, including mathematics, logical reasoning, and Chinese chemistry, demonstrate that CP-Router efficiently reduces token usage while maintaining or even improving accuracy compared to using LRM alone. We also extend CP-Router to diverse model pairings and open-ended QA, where it continues to demonstrate strong performance, validating its generality and robustness.
The Massive Multitask Language Understanding (MMLU) benchmark has been widely used to evaluate language models across various domains. However, existing MMLU datasets primarily focus on high-resource languages such as English, which leaves low-resource languages like Bengali underrepresented. In this paper, we introduce BnMMLU, a benchmark to evaluate the multitask language understanding capabilities of Bengali in language models. The dataset spans 23 domains, including science, humanities, mathematics and general knowledge and is structured in a multiple-choice format to assess factual knowledge, application-based problem-solving and reasoning abilities of language models. It consists of 138,949 question-option pairs. We benchmark several proprietary and open-source large language models (LLMs) on the BnMMLU test set. Additionally, we annotate the test set with three cognitive categories-factual knowledge, procedural application and reasoning-to gain deeper insights into model strengths and weaknesses across various cognitive tasks. The results reveal significant performance gaps, highlighting the need for improved pre-training and fine-tuning strategies tailored to Bengali data. We release the dataset and benchmark results to facilitate further research in this area.
Digital Forensics and Incident Response (DFIR) involves analyzing digital evidence to support legal investigations. Large Language Models (LLMs) offer new opportunities in DFIR tasks such as log analysis and memory forensics, but their susceptibility to errors and hallucinations raises concerns in high-stakes contexts. Despite growing interest, there is no comprehensive benchmark to evaluate LLMs across both theoretical and practical DFIR domains. To address this gap, we present DFIR-Metric, a benchmark with three components: (1) Knowledge Assessment: a set of 700 expert-reviewed multiple-choice questions sourced from industry-standard certifications and official documentation; (2) Realistic Forensic Challenges: 150 CTF-style tasks testing multi-step reasoning and evidence correlation; and (3) Practical Analysis: 500 disk and memory forensics cases from the NIST Computer Forensics Tool Testing Program (CFTT). We evaluated 14 LLMs using DFIR-Metric, analyzing both their accuracy and consistency across trials. We also introduce a new metric, the Task Understanding Score (TUS), designed to more effectively evaluate models in scenarios where they achieve near-zero accuracy. This benchmark offers a rigorous, reproducible foundation for advancing AI in digital forensics. All scripts, artifacts, and results are available on the project website at https://github.com/DFIR-Metric.
Recent Multimodal Large Language Models (MLLMs) achieve promising performance on visual and audio benchmarks independently. However, the ability of these models to process cross-modal information synchronously remains largely unexplored. In this paper, we introduce: 1) Daily-Omni, an Audio-Visual Questioning and Answering benchmark comprising 684 videos of daily life scenarios from diverse sources, rich in both audio and visual information, and featuring 1197 multiple-choice QA pairs across 6 major tasks; 2) Daily-Omni QA Generation Pipeline, which includes automatic annotation, QA generation and QA optimization, significantly improves efficiency for human evaluation and scalability of the benchmark; 3) Daily-Omni-Agent, a training-free agent utilizing open-source Visual Language Model (VLM), Audio Language Model (ALM) and Automatic Speech Recognition (ASR) model to establish a baseline for this benchmark. The results show that current MLLMs still struggle significantly with tasks requiring audio-visual integration, but combining VLMs and ALMs with simple temporal alignment techniques can achieve substantially better performance. Codes and benchmark are available at \href{https://github.com/Lliar-liar/Daily-Omni}{https://github.com/Lliar-liar/Daily-Omni}.
Empowered by vast internal knowledge reservoir, the new generation of large language models (LLMs) demonstrate untapped potential to tackle medical tasks. However, there is insufficient effort made towards summoning up a synergic effect from multiple LLMs' expertise and background. In this study, we propose a multi-LLM collaboration framework tailored on a medical multiple-choice questions dataset. Through post-hoc analysis on 3 pre-trained LLM participants, our framework is proved to boost all LLMs reasoning ability as well as alleviate their divergence among questions. We also measure an LLM's confidence when it confronts with adversary opinions from other LLMs and observe a concurrence between LLM's confidence and prediction accuracy.
We introduce KoBALT (Korean Benchmark for Advanced Linguistic Tasks), a comprehensive linguistically-motivated benchmark comprising 700 multiple-choice questions spanning 24 phenomena across five linguistic domains: syntax, semantics, pragmatics, phonetics/phonology, and morphology. KoBALT is designed to advance the evaluation of large language models (LLMs) in Korean, a morphologically rich language, by addressing the limitations of conventional benchmarks that often lack linguistic depth and typological grounding. It introduces a suite of expert-curated, linguistically motivated questions with minimal n-gram overlap with standard Korean corpora, substantially mitigating the risk of data contamination and allowing a more robust assessment of true language understanding. Our evaluation of 20 contemporary LLMs reveals significant performance disparities, with the highest-performing model achieving 61\% general accuracy but showing substantial variation across linguistic domains - from stronger performance in semantics (66\%) to considerable weaknesses in phonology (31\%) and morphology (36\%). Through human preference evaluation with 95 annotators, we demonstrate a strong correlation between KoBALT scores and human judgments, validating our benchmark's effectiveness as a discriminative measure of Korean language understanding. KoBALT addresses critical gaps in linguistic evaluation for typologically diverse languages and provides a robust framework for assessing genuine linguistic competence in Korean language models.
Students often do not fully understand the code they have written. This sometimes does not become evident until later in their education, which can mean it is harder to fix their incorrect knowledge or misunderstandings. In addition, being able to fully understand code is increasingly important in a world where students have access to generative artificial intelligence (GenAI) tools, such as GitHub Copilot. One effective solution is to utilise code comprehension questions, where a marker asks questions about a submission to gauge understanding, this can also have the side effect of helping to detect plagiarism. However, this approach is time consuming and can be difficult and/or expensive to scale. This paper introduces AutoMCQ, which uses GenAI for the automatic generation of multiple-choice code comprehension questions. This is integrated with the CodeRunner automated assessment platform.
Metaphorical comprehension in images remains a critical challenge for AI systems, as existing models struggle to grasp the nuanced cultural, emotional, and contextual implications embedded in visual content. While multimodal large language models (MLLMs) excel in basic Visual Question Answer (VQA) tasks, they struggle with a fundamental limitation on image implication tasks: contextual gaps that obscure the relationships between different visual elements and their abstract meanings. Inspired by the human cognitive process, we propose Let Androids Dream (LAD), a novel framework for image implication understanding and reasoning. LAD addresses contextual missing through the three-stage framework: (1) Perception: converting visual information into rich and multi-level textual representations, (2) Search: iteratively searching and integrating cross-domain knowledge to resolve ambiguity, and (3) Reasoning: generating context-alignment image implication via explicit reasoning. Our framework with the lightweight GPT-4o-mini model achieves SOTA performance compared to 15+ MLLMs on English image implication benchmark and a huge improvement on Chinese benchmark, performing comparable with the GPT-4o model on Multiple-Choice Question (MCQ) and outperforms 36.7% on Open-Style Question (OSQ). Additionally, our work provides new insights into how AI can more effectively interpret image implications, advancing the field of vision-language reasoning and human-AI interaction. Our project is publicly available at https://github.com/MING-ZCH/Let-Androids-Dream-of-Electric-Sheep.
Large Language Models (LLMs) are increasingly evaluated on multiple-choice question answering (MCQA) tasks using *first-token probability* (FTP), which selects the answer option whose initial token has the highest likelihood. While efficient, FTP can be fragile: models may assign high probability to unrelated tokens (*misalignment*) or use a valid token merely as part of a generic preamble rather than as a clear answer choice (*misinterpretation*), undermining the reliability of symbolic evaluation. We propose a simple solution: the *prefilling attack*, a structured natural-language prefix (e.g., "*The correct option is:*") prepended to the model output. Originally explored in AI safety, we repurpose prefilling to steer the model to respond with a clean, valid option, without modifying its parameters. Empirically, the FTP with prefilling strategy substantially improves accuracy, calibration, and output consistency across a broad set of LLMs and MCQA benchmarks. It outperforms standard FTP and often matches the performance of open-ended generation approaches that require full decoding and external classifiers, while being significantly more efficient. Our findings suggest that prefilling is a simple, robust, and low-cost method to enhance the reliability of FTP-based evaluation in multiple-choice settings.
Vision-Language Models (VLMs) have demonstrated impressive capabilities across a range of tasks, yet concerns about their potential biases exist. This work investigates the extent to which prominent VLMs exhibit cultural biases by evaluating their performance on an image-based country identification task at a country level. Utilizing the geographically diverse Country211 dataset, we probe several large vision language models (VLMs) under various prompting strategies: open-ended questions, multiple-choice questions (MCQs) including challenging setups like multilingual and adversarial settings. Our analysis aims to uncover disparities in model accuracy across different countries and question formats, providing insights into how training data distribution and evaluation methodologies might influence cultural biases in VLMs. The findings highlight significant variations in performance, suggesting that while VLMs possess considerable visual understanding, they inherit biases from their pre-training data and scale that impact their ability to generalize uniformly across diverse global contexts.
While large language models (LLMs) demonstrate impressive capabilities across numerous applications, their robustness remains a critical concern. This paper is motivated by a specific vulnerability: the order sensitivity of LLMs. This vulnerability manifests itself as the order bias observed when LLMs decide between possible options (for example, a preference for the first option) and the tendency of LLMs to provide different answers when options are reordered. The use cases for this scenario extend beyond the classical case of multiple-choice question answering to the use of LLMs as automated evaluators in AI pipelines, comparing output generated by different models. We introduce Set-LLM, a novel architectural adaptation for pretrained LLMs that enables the processing of mixed set-text inputs with permutation invariance guarantees. The adaptations involve a new attention mask and new positional encodings specifically designed for sets. We provide a theoretical proof of invariance and demonstrate through experiments that Set-LLM can be trained effectively, achieving comparable or improved performance and maintaining the runtime of the original model, while eliminating order sensitivity.
Vision-Language Models (VLMs) acquire real-world knowledge and general reasoning ability through Internet-scale image-text corpora. They can augment robotic systems with scene understanding and task planning, and assist visuomotor policies that are trained on robot trajectory data. We explore the reverse paradigm - using rich, real, multi-modal robot trajectory data to enhance and evaluate VLMs. In this paper, we present Robo2VLM, a Visual Question Answering (VQA) dataset generation framework for VLMs. Given a human tele-operated robot trajectory, Robo2VLM derives ground-truth from non-visual and non-descriptive sensory modalities, such as end-effector pose, gripper aperture, and force sensing. Based on these modalities, it segments the robot trajectory into a sequence of manipulation phases. At each phase, Robo2VLM uses scene and interaction understanding to identify 3D properties of the robot, task goal, and the target object. The properties are used to generate representative VQA queries - images with textural multiple-choice questions - based on spatial, goal-conditioned, and interaction reasoning question templates. We curate Robo2VLM-1, a large-scale in-the-wild dataset with 684,710 questions covering 463 distinct scenes and 3,396 robotic manipulation tasks from 176k real robot trajectories. Results suggest that Robo2VLM-1 can benchmark and improve VLM capabilities in spatial and interaction reasoning.
Large Language Models (LLMs) have achieved impressive results across a broad array of tasks, yet their capacity for complex, domain-specific mathematical reasoning-particularly in wireless communications-remains underexplored. In this work, we introduce WirelessMathBench, a novel benchmark specifically designed to evaluate LLMs on mathematical modeling challenges to wireless communications engineering. Our benchmark consists of 587 meticulously curated questions sourced from 40 state-of-the-art research papers, encompassing a diverse spectrum of tasks ranging from basic multiple-choice questions to complex equation completion tasks, including both partial and full completions, all of which rigorously adhere to physical and dimensional constraints. Through extensive experimentation with leading LLMs, we observe that while many models excel in basic recall tasks, their performance degrades significantly when reconstructing partially or fully obscured equations, exposing fundamental limitations in current LLMs. Even DeepSeek-R1, the best performer on our benchmark, achieves an average accuracy of only 38.05%, with a mere 7.83% success rate in full equation completion. By publicly releasing WirelessMathBench along with the evaluation toolkit, we aim to advance the development of more robust, domain-aware LLMs for wireless system analysis and broader engineering applications.
Large multimodal models (LMMs) have recently emerged as a powerful tool for long video understanding (LVU), prompting the development of standardized LVU benchmarks to evaluate their performance. However, our investigation reveals a rather sober lesson for existing LVU benchmarks. First, most existing benchmarks rely heavily on multiple-choice questions (MCQs), whose evaluation results are inflated due to the possibility of guessing the correct answer; Second, a significant portion of questions in these benchmarks have strong priors to allow models to answer directly without even reading the input video. For example, Gemini-1.5-Pro can achieve over 50\% accuracy given a random frame from a long video on Video-MME. We also observe that increasing the number of frames does not necessarily lead to improvement on existing benchmarks, which is counterintuitive. As a result, the validity and robustness of current LVU benchmarks are undermined, impeding a faithful assessment of LMMs' long-video understanding capability. To tackle this problem, we propose VideoEval-Pro, a realistic LVU benchmark containing questions with open-ended short-answer, which truly require understanding the entire video. VideoEval-Pro assesses both segment-level and full-video understanding through perception and reasoning tasks. By evaluating 21 proprietary and open-source video LMMs, we conclude the following findings: (1) video LMMs show drastic performance ($>$25\%) drops on open-ended questions compared with MCQs; (2) surprisingly, higher MCQ scores do not lead to higher open-ended scores on VideoEval-Pro; (3) compared to other MCQ benchmarks, VideoEval-Pro benefits more from increasing the number of input frames. Our results show that VideoEval-Pro offers a more realistic and reliable measure of long video understanding, providing a clearer view of progress in this domain.
Recent advances in Large Language Models (LLMs) have demonstrated promising knowledge and reasoning abilities, yet their performance in multilingual and low-resource settings remains underexplored. Existing benchmarks often exhibit cultural bias, restrict evaluation to text-only, rely on multiple-choice formats, and, more importantly, are limited for extremely low-resource languages. To address these gaps, we introduce IRLBench, presented in parallel English and Irish, which is considered definitely endangered by UNESCO. Our benchmark consists of 12 representative subjects developed from the 2024 Irish Leaving Certificate exams, enabling fine-grained analysis of model capabilities across domains. By framing the task as long-form generation and leveraging the official marking scheme, it does not only support a comprehensive evaluation of correctness but also language fidelity. Our extensive experiments of leading closed-source and open-source LLMs reveal a persistent performance gap between English and Irish, in which models produce valid Irish responses less than 80\% of the time, and answer correctly 55.8\% of the time compared to 76.2\% in English for the best-performing model. We release IRLBench (https://huggingface.co/datasets/ReliableAI/IRLBench) and an accompanying evaluation codebase (https://github.com/ReML-AI/IRLBench) to enable future research on robust, culturally aware multilingual AI development.
Clinical guidelines, typically structured as decision trees, are central to evidence-based medical practice and critical for ensuring safe and accurate diagnostic decision-making. However, it remains unclear whether Large Language Models (LLMs) can reliably follow such structured protocols. In this work, we introduce MedGUIDE, a new benchmark for evaluating LLMs on their ability to make guideline-consistent clinical decisions. MedGUIDE is constructed from 55 curated NCCN decision trees across 17 cancer types and uses clinical scenarios generated by LLMs to create a large pool of multiple-choice diagnostic questions. We apply a two-stage quality selection process, combining expert-labeled reward models and LLM-as-a-judge ensembles across ten clinical and linguistic criteria, to select 7,747 high-quality samples. We evaluate 25 LLMs spanning general-purpose, open-source, and medically specialized models, and find that even domain-specific LLMs often underperform on tasks requiring structured guideline adherence. We also test whether performance can be improved via in-context guideline inclusion or continued pretraining. Our findings underscore the importance of MedGUIDE in assessing whether LLMs can operate safely within the procedural frameworks expected in real-world clinical settings.
Recent progress in large language models (LLMs) has outpaced the development of effective evaluation methods. Traditional benchmarks rely on task-specific metrics and static datasets, which often suffer from fairness issues, limited scalability, and contamination risks. In this paper, we introduce Teach2Eval, an indirect evaluation framework inspired by the Feynman Technique. Instead of directly testing LLMs on predefined tasks, our method evaluates a model's multiple abilities to teach weaker student models to perform tasks effectively. By converting open-ended tasks into standardized multiple-choice questions (MCQs) through teacher-generated feedback, Teach2Eval enables scalable, automated, and multi-dimensional assessment. Our approach not only avoids data leakage and memorization but also captures a broad range of cognitive abilities that are orthogonal to current benchmarks. Experimental results across 26 leading LLMs show strong alignment with existing human and model-based dynamic rankings, while offering additional interpretability for training guidance.