We study LLM judgments of misinformation expressed with uncertainty. Our experiments study the response of three widely used LLMs (GPT-4o, LLaMA3, DeepSeek-v2) to misinformation propositions that have been verified false and then are transformed into uncertain statements according to an uncertainty typology. Our results show that after transformation, LLMs change their factchecking classification from false to not-false in 25% of the cases. Analysis reveals that the change cannot be explained by predictors to which humans are expected to be sensitive, i.e., modality, linguistic cues, or argumentation strategy. The exception is doxastic transformations, which use linguistic cue phrases such as "It is believed... ". To gain further insight, we prompt the LLM to make another judgment about the transformed misinformation statements that is not related to truth value. Specifically, we study LLM estimates of the frequency with which people make the uncertain statement. We find a small but significant correlation between judgment of fact and estimation of frequency.

Computing students increasingly rely on generative AI tools for programming assistance, often without formal instruction or guidance. This highlights a need to teach students how to effectively interact with AI models, particularly through natural language prompts, to generate and critically evaluate code for solving computational tasks. To address this, we developed a novel platform for prompt programming that enables authentic dialogue-based interactions, supports problems involving multiple interdependent functions, and offers on-request execution of generated code. Data analysis from over 900 students in an introductory programming course revealed high engagement, with the majority of prompts occurring within multi-turn dialogues. Problems with multiple interdependent functions encouraged iterative refinement, with progression graphs highlighting several common strategies. Students were highly selective about the code they chose to test, suggesting that on-request execution of generated code promoted critical thinking. Given the growing importance of learning dialogue-based programming with AI, we provide this tool as a publicly accessible resource, accompanied by a corpus of programming problems for educational use.

In today's data-driven era, computational systems generate vast amounts of data that drive the digital transformation of industries, where Artificial Intelligence (AI) plays a key role. Currently, the demand for eXplainable AI (XAI) has increased to enhance the interpretability, transparency, and trustworthiness of AI models. However, evaluating XAI methods remains challenging: existing evaluation frameworks typically focus on quantitative properties such as fidelity, consistency, and stability without taking into account qualitative characteristics such as satisfaction and interpretability. In addition, practitioners face a lack of guidance in selecting appropriate datasets, AI models, and XAI methods -a major hurdle in human-AI collaboration. To address these gaps, we propose a framework that integrates quantitative benchmarking with qualitative user assessments through virtual personas based on the "Anthology" of backstories of the Large Language Model (LLM). Our framework also incorporates a content-based recommender system that leverages dataset-specific characteristics to match new input data with a repository of benchmarked datasets. This yields an estimated XAI score and provides tailored recommendations for both the optimal AI model and the XAI method for a given scenario.

With the continued migration of storage to cloud database systems,the impact of slow queries in such systems on services and user experience is increasing. Root-cause diagnosis plays an indispensable role in facilitating slow-query detection and revision. This paper proposes a method capable of both identifying possible root cause types for slow queries and ranking these according to their potential for accelerating slow queries. This enables prioritizing root causes with the highest impact, in turn improving slow-query revision effectiveness. To enable more accurate and detailed diagnoses, we propose the multimodal Ranking for the Root Causes of slow queries (RCRank) framework, which formulates root cause analysis as a multimodal machine learning problem and leverages multimodal information from query statements, execution plans, execution logs, and key performance indicators. To obtain expressive embeddings from its heterogeneous multimodal input, RCRank integrates self-supervised pre-training that enhances cross-modal alignment and task relevance. Next, the framework integrates root-cause-adaptive cross Transformers that enable adaptive fusion of multimodal features with varying characteristics. Finally, the framework offers a unified model that features an impact-aware training objective for identifying and ranking root causes. We report on experiments on real and synthetic datasets, finding that RCRank is capable of consistently outperforming the state-of-the-art methods at root cause identification and ranking according to a range of metrics.

Aligning powerful AI models on tasks that surpass human evaluation capabilities is the central problem of \textbf{superalignment}. To address this problem, weak-to-strong generalization aims to elicit the capabilities of strong models through weak supervisors and ensure that the behavior of strong models aligns with the intentions of weak supervisors without unsafe behaviors such as deception. Although weak-to-strong generalization exhibiting certain generalization capabilities, strong models exhibit significant overfitting in weak-to-strong generalization: Due to the strong fit ability of strong models, erroneous labels from weak supervisors may lead to overfitting in strong models. In addition, simply filtering out incorrect labels may lead to a degeneration in question quality, resulting in a weak generalization ability of strong models on hard questions. To mitigate overfitting in weak-to-strong generalization, we propose a two-stage framework that simultaneously improves the quality of supervision signals and the quality of input questions. Experimental results in three series of large language models and two mathematical benchmarks demonstrate that our framework significantly improves PGR compared to naive weak-to-strong generalization, even achieving up to 100\% PGR on some models.

Modern Large Language Models (LLMs) have shown astounding capabilities of code understanding and synthesis. In order to assess such capabilities, several benchmarks have been devised (e.g., HumanEval). However, most benchmarks focus on code synthesis from natural language instructions. Hence, such benchmarks do not test for other forms of code understanding. Moreover, there have been concerns about contamination and leakage. That is, benchmark problems (or closely related problems) may appear in training set, strongly biasing benchmark results. In this work we investigate whether large language models can correctly predict runtime program behavior. To this end, we introduce ThrowBench, a benchmark consisting of over 2,400 short user-written programs written in four different programming languages. The majority of these programs throw an exception during runtime (due to a bug). LLMs are asked to predict whether a presented program throws an exception and, if so, which one. Evaluating our benchmark on six state-of-the-art code LLMs we see modest performance ranging from 19 to 38% (F1 score). Benchmarking a wider set of code capabilities could improve the assessment of code LLMs and help identify weak points in current models. Moreover, as ground-truth answers have been determined through program execution, leakage is not a concern. We release ThrowBench as well as all of our results together with this work.

We introduce FuseChat-3.0, a suite of large language models (LLMs) developed by integrating the strengths of heterogeneous source LLMs into more compact target LLMs. Our source models include the powerful Gemma-2-27B-it, Mistral-Large-Instruct-2407, Qwen-2.5-72B-Instruct, and Llama-3.1-70B-Instruct. To leverage the diverse capabilities of these source models, we develop a specialized data construction protocol tailored to various tasks and domains. The FuseChat-3.0 training pipeline consists of two key stages: (1) supervised fine-tuning (SFT) to align the target and source model distributions, and (2) Direct Preference Optimization (DPO) to apply preferences from multiple source LLMs to fine-tune the target model. As illustrated in Figure 1, using Llama-3.1-8B-Instruct as the target model, our fusion approach achieves an average improvement of 6.8 points across 14 benchmarks. Moreover, it demonstrates remarkable gains of 37.1 points and 30.1 points on the instruction-following benchmarks AlpacaEval-2 and Arena-Hard, respectively. Combining the strengths of multiple large language models (LLMs) provides a powerful means to enhance performance, robustness, and generalization across diverse tasks by leveraging the unique expertise and knowledge each model offers. Individual LLMs, particularly those constrained by size or training data, may perform well in specific areas but struggle in others due to specialization gaps. For instance, one model might excel at generating creative content but lack precision in technical explanations, while another delivers technical accuracy but struggles with conversational fluency.

RGB-Thermal fusion is a potential solution for various weather and light conditions in challenging scenarios. However, plenty of studies focus on designing complex modules to fuse different modalities. With the widespread application of large language models (LLMs), valuable information can be more effectively extracted from natural language. Therefore, we aim to leverage the advantages of large language models to design a structurally simple and highly adaptable multimodal fusion model architecture. We proposed MultimodAl Segmentation with TExt PRompts (MASTER) architecture, which integrates LLM into the fusion of RGB-Thermal multimodal data and allows complex query text to participate in the fusion process. Our model utilizes a dual-path structure to extract information from different modalities of images. Additionally, we employ LLM as the core module for multimodal fusion, enabling the model to generate learnable codebook tokens from RGB, thermal images, and textual information. A lightweight image decoder is used to obtain semantic segmentation results. The proposed MASTER performs exceptionally well in benchmark tests across various automated driving scenarios, yielding promising results.

Temporal progression is an integral part of knowledge accumulation and update. Web search is frequently adopted as grounding for agent knowledge, yet its inappropriate configuration affects the quality of agent responses. Here, we construct a tool-based out-of-sample testing framework to measure the knowledge variability of large language model (LLM) agents from distinct date-controlled tools (DCTs). We demonstrate the temporal effects of an LLM agent as a writing assistant, which can use web search to help complete scientific publication abstracts. We show that temporal effects of the search engine translates into tool-dependent agent performance but can be alleviated with base model choice and explicit reasoning instructions such as chain-of-thought prompting. Our results indicate that agent evaluation should take a dynamical view and account for the temporal influence of tools and the updates of external resources.

Tasks such as chronic disease Large language models (LLMs) have emerged management, multi-visit care planning, and patient history as promising tools for assisting in medical tasks, synthesis require clinicians to understand complex relationships yet processing Electronic Health Records (EHRs) between different record entries and how past events presents unique challenges due to their longitudinal influence current and future clinical decisions (Wornow nature. While LLMs' capabilities to perform et al., 2024). The cognitive demands of processing such medical tasks continue to improve, their ability lengthy documentation are significant. While biomedical to reason over temporal dependencies across LLMs have shown promising results on well-structured multiple patient visits and time frames remains tasks like answering USMLE questions and medical knowledge unexplored. We introduce TIMER (Temporal retrieval (Singhal et al., 2023; Lu et al., 2024; Lucas Instruction Modeling and Evaluation for Longitudinal et al., 2024), recent evaluations reveal their significant limitations Clinical Records), a framework that incorporate in processing longitudinal patient information and in instruction-response pairs grounding to making clinical decisions over time (Hager et al., 2024; Bedi different parts of a patient's record as a critical et al., 2024). The gap between isolated question-answering dimension in both instruction evaluation and tuning performance and temporal reasoning ability impacts the for longitudinal clinical records. We develop practical utility of LLMs in healthcare. While there is some TIMER-Bench, the first time-aware benchmark prior work that has explored temporal understanding abilities that evaluates temporal reasoning capabilities over of general LLMs (Wang & Zhao, 2024; Fatemi et al., longitudinal EHRs, as well as TIMER-Instruct, 2024; Herel et al., 2024), how these capabilities scale to an instruction-tuning methodology for LLMs to longer contexts remains understudied, particularly in healthcare learn reasoning over time. We demonstrate that where longitudinal reasoning is important.