Practitioners increasingly rely on Large Language Models (LLMs) to evaluate generative AI outputs through "LLM-as-a-Judge" approaches. However, these methods produce holistic scores that obscure which specific elements influenced the assessments. We propose functional fragmentation, a method that dissects each output into key fragments and interprets the rhetoric functions that each fragment serves relative to evaluation criteria -- surfacing the elements of interest and revealing how they fulfill or hinder user goals. We instantiate this approach in Evalet, an interactive system that visualizes fragment-level functions across many outputs to support inspection, rating, and comparison of evaluations. A user study (N=10) found that, while practitioners struggled to validate holistic scores, our approach helped them identify 48% more evaluation misalignments. This helped them calibrate trust in LLM evaluations and rely on them to find more actionable issues in model outputs. Our work shifts LLM evaluation from quantitative scores toward qualitative, fine-grained analysis of model behavior.

As artificial intelligence (AI) systems permeate critical sectors, the need for professionals who can address ethical, legal and governance challenges has become urgent. Current AI ethics education remains fragmented, often siloed by discipline and disconnected from practice. This paper synthesizes literature and regulatory developments to propose a modular, interdisciplinary curriculum that integrates technical foundations with ethics, law and policy. We highlight recurring operational failures in AI - bias, misspecified objectives, generalization errors, misuse and governance breakdowns - and link them to pedagogical strategies for teaching AI governance. Drawing on perspectives from the EU, China and international frameworks, we outline a semester plan that emphasizes integrated ethics, stakeholder engagement and experiential learning. The curriculum aims to prepare students to diagnose risks, navigate regulation and engage diverse stakeholders, fostering adaptive and ethically grounded professionals for responsible AI governance.

Most previous work on Conversational Query Rewriting employs an end-to-end rewriting paradigm. However, this approach is hindered by the issue of multiple fuzzy expressions within the query, which complicates the simultaneous identification and rewriting of multiple positions. To address this issue, we propose a novel framework ICR (Iterative Clarification and Rewriting), an iterative rewriting scheme that pivots on clarification questions. Within this framework, the model alternates between generating clarification questions and rewritten queries. The experimental results show that our ICR can continuously improve retrieval performance in the clarification-rewriting iterative process, thereby achieving state-of-the-art performance on two popular datasets.

The arrival of AI coding assistants in educational settings presents a paradigm shift, introducing a "new kid in the classroom" for both students and instructors. Thus, understanding the perceptions of these key actors about this new dynamic is critical. This exploratory study contributes to this area by investigating how these tools are shaping the experiences of novice programmers in an introductory programming course. Through a two-part exam, we investigated student perceptions by first providing access to AI support for a programming task and then requiring an extension of the solution without it. We collected Likert-scale and open-ended responses from 20 students to understand their perceptions on the challenges they faced. Our findings reveal that students perceived AI tools as helpful for grasping code concepts and boosting their confidence during the initial development phase. However, a noticeable difficulty emerged when students were asked to work unaided, pointing to potential overreliance and gaps in foundational knowledge transfer. These insights highlight a critical need for new pedagogical approaches that integrate AI effectively while effectively enhancing core programming skills, rather than impersonating them.

In visual question answering (VQA) context, users often pose ambiguous questions to visual language models (VLMs) due to varying expression habits. Existing research addresses such ambiguities primarily by rephrasing questions. These approaches neglect the inherently interactive nature of user interactions with VLMs, where ambiguities can be clarified through user feedback. However, research on interactive clarification faces two major challenges: (1) Benchmarks are absent to assess VLMs' capacity for resolving ambiguities through interaction; (2) VLMs are trained to prefer answering rather than asking, preventing them from seeking clarification. To overcome these challenges, we introduce \textbf{ClearVQA} benchmark, which targets three common categories of ambiguity in VQA context, and encompasses various VQA scenarios.

Continuous representations of logic formulae allow us to integrate symbolic knowledge into data-driven learning algorithms. If such embeddings are semantically consistent, i.e. if similar specifications are mapped into nearby vectors, they enable continuous learning and optimization directly in the semantic space of formulae. However, to translate the optimal continuous representation into a concrete requirement, such embeddings must be invertible. We tackle this issue by training a Transformer-based decoder-only model to invert semantic embeddings of Signal Temporal Logic (STL) formulae. STL is a powerful formalism that allows us to describe properties of signals varying over time in an expressive yet concise way. By constructing a small vocabulary from STL syntax, we demonstrate that our proposed model is able to generate valid formulae after only 1 epoch and to generalize to the semantics of the logic in about 10 epochs. Additionally, the model is able to decode a given embedding into formulae that are often simpler in terms of length and nesting while remaining semantically close (or equivalent) to gold references. We show the effectiveness of our methodology across various levels of training formulae complexity to assess the impact of training data on the model's ability to effectively capture the semantic information contained in the embeddings and generalize out-of-distribution. Finally, we deploy our model for solving a requirement mining task, i.e. inferring STL specifications that solve a classification task on trajectories, performing the optimization directly in the semantic space.

Large Language Models (LLMs) often exhibit \textit{hallucinations}, generating factually incorrect or semantically irrelevant content in response to prompts. Chain-of-Thought (CoT) prompting can mitigate hallucinations by encouraging step-by-step reasoning, but its impact on hallucination detection remains underexplored. To bridge this gap, we conduct a systematic empirical evaluation. We begin with a pilot experiment, revealing that CoT reasoning significantly affects the LLM's internal states and token probability distributions. Building on this, we evaluate the impact of various CoT prompting methods on mainstream hallucination detection methods across both instruction-tuned and reasoning-oriented LLMs. Specifically, we examine three key dimensions: changes in hallucination score distributions, variations in detection accuracy, and shifts in detection confidence. Our findings show that while CoT prompting helps reduce hallucination frequency, it also tends to obscure critical signals used for detection, impairing the effectiveness of various detection methods. Our study highlights an overlooked trade-off in the use of reasoning. Code is publicly available at: https://github.com/ECNU-Text-Computing/cot-hallu-detect .

Abstract-- Traditional soil sampling and analysis methods are labor-intensive, time-consuming, and limited in spatial resolution, making them unsuitable for large-scale precision agriculture. T o address these limitations, we present a robotic solution for real-time sampling, analysis and mapping of key soil properties. Our system consists of two main sub-systems: a Sample Acquisition System (SAS) for precise, automated in-field soil sampling; and a Sample Analysis Lab (Lab) for real-time soil property analysis. The system's performance was validated through extensive field trials at a large-scale Australian farm. Experimental results show that the SAS can consistently acquire soil samples with a mass of 50g at a depth of 200mm, while the Lab can process each sample within 10 minutes to accurately measure pH and macronutrients. These results demonstrate the potential of the system to provide farmers with timely, data-driven insights for more efficient and sustainable soil management and fertilizer application. I. INTRODUCTION Achieving sustainable agricultural resource management requires accurate, high-resolution, and up-to-date data on soil properties such as pH and macronutrients [1], [2]. However, conventional soil sampling and testing methods fail to address this need at scale.

Iterative evaluation of LLMs during training is essential to ensure expected capability development, but can be time- and compute-intensive. While NLU tasks, where the model selects from fixed answer choices, are cheap to evaluate, essential capabilities like reasoning and code generation rely on the more time-consuming NLG (token-by-token generation) format. In this work, our aim is to decrease the computational burden of NLG benchmarks in order to enable monitoring crucial LLM capabilities during model training. We reformulate generative tasks into computationally cheaper NLU alternatives. We test the performance correlation between the original and reformulated tasks using 8 LMs of various sizes and 4 capabilities: mathematical reasoning, code generation, factual knowledge and reading comprehension. Our results show a strong correlation between task formats, supporting capability assessment via cheaper alternatives and achieving over 35x average reduction in evaluation time. Our project is available at: https://github.com/Fraunhofer-IIS/EvalShortcut

Navigational signs are common aids for human wayfinding and scene understanding, but are underutilized by robots. We argue that they benefit robot navigation and scene understanding, by directly encoding privileged information on actions, spatial regions, and relations. Interpreting signs in open-world settings remains a challenge owing to the complexity of scenes and signs, but recent advances in vision-language models (VLMs) make this feasible. To advance progress in this area, we introduce the task of navigational sign understanding which parses locations and associated directions from signs. We offer a benchmark for this task, proposing appropriate evaluation metrics and curating a test set capturing signs with varying complexity and design across diverse public spaces, from hospitals to shopping malls to transport hubs. We also provide a baseline approach using VLMs, and demonstrate their promise on navigational sign understanding. Code and dataset are available on Github.