Multimodal Large Language Models (MLLMs) have shown promising capabilities in mathematical reasoning within visual contexts across various datasets. However, most existing multimodal math benchmarks are limited to single-visual contexts, which diverges from the multi-visual scenarios commonly encountered in real-world mathematical applications. To address this gap, we introduce MV-MATH: a meticulously curated dataset of 2,009 high-quality mathematical problems. Each problem integrates multiple images interleaved with text, derived from authentic K-12 scenarios, and enriched with detailed annotations. MV-MATH includes multiple-choice, free-form, and multi-step questions, covering 11 subject areas across 3 difficulty levels, and serves as a comprehensive and rigorous benchmark for assessing MLLMs' mathematical reasoning in multi-visual contexts. Through extensive experimentation, we observe that MLLMs encounter substantial challenges in multi-visual math tasks, with a considerable performance gap relative to human capabilities on MV-MATH. Furthermore, we analyze the performance and error patterns of various models, providing insights into MLLMs' mathematical reasoning capabilities within multi-visual settings.

Noise in data appears to be inevitable in most real-world machine learning applications and would cause severe overfitting problems. Not only can data features contain noise, but labels are also prone to be noisy due to human input. In this paper, rather than noisy label learning in multiclass classifications, we instead focus on the less explored area of noisy label learning for multilabel classifications. Specifically, we investigate the post-correction of predictions generated from classifiers learned with noisy labels. The reasons are two-fold. Firstly, this approach can directly work with the trained models to save computational resources. Secondly, it could be applied on top of other noisy label correction techniques to achieve further improvements. To handle this problem, we appeal to deep generative approaches that are possible for uncertainty estimation. Our model posits that label noise arises from a stochastic shift in the latent variable, providing a more robust and beneficial means for noisy learning. We develop both unsupervised and semi-supervised learning methods for our model. The extensive empirical study presents solid evidence to that our approach is able to consistently improve the independent models and performs better than a number of existing methods across various noisy label settings. Moreover, a comprehensive empirical analysis of the proposed method is carried out to validate its robustness, including sensitivity analysis and an ablation study, among other elements.

Applications of Large Language Models (LLMs) are rapidly growing in industry and academia for various software engineering (SE) tasks. As these models become more integral to critical processes, ensuring their reliability and trustworthiness becomes essential. Consequently, the concept of trust in these systems is becoming increasingly critical. Well-calibrated trust is important, as excessive trust can lead to security vulnerabilities, and risks, while insufficient trust can hinder innovation. However, the landscape of trust-related concepts in LLMs in SE is relatively unclear, with concepts such as trust, distrust, and trustworthiness lacking clear conceptualizations in the SE community. To bring clarity to the current research status and identify opportunities for future work, we conducted a comprehensive review of $88$ papers: a systematic literature review of $18$ papers focused on LLMs in SE, complemented by an analysis of 70 papers from broader trust literature. Additionally, we conducted a survey study with 25 domain experts to gain insights into practitioners' understanding of trust and identify gaps between existing literature and developers' perceptions. The result of our analysis serves as a roadmap that covers trust-related concepts in LLMs in SE and highlights areas for future exploration.

Retrieval-Augmented Generation (RAG) has gained significant attention in recent years for its potential to enhance natural language understanding and generation by combining large-scale retrieval systems with generative models. RAG leverages external knowledge sources, such as documents, databases, or structured data, to improve model performance and generate more accurate and contextually relevant outputs. This survey aims to provide a comprehensive overview of RAG by examining its fundamental components, including retrieval mechanisms, generation processes, and the integration between the two. We discuss the key characteristics of RAG, such as its ability to augment generative models with dynamic external knowledge, and the challenges associated with aligning retrieved information with generative objectives. We also present a taxonomy that categorizes RAG methods, ranging from basic retrieval-augmented approaches to more advanced models incorporating multi-modal data and reasoning capabilities. Additionally, we review the evaluation benchmarks and datasets commonly used to assess RAG systems, along with a detailed exploration of its applications in fields such as question answering, summarization, and information retrieval. Finally, we highlight emerging research directions and opportunities for improving RAG systems, such as enhanced retrieval efficiency, model interpretability, and domain-specific adaptations. This paper concludes by outlining the prospects for RAG in addressing real-world challenges and its potential to drive further advancements in natural language processing.

We introduce an Item Response Theory (IRT)-based framework to detect and quantify socioeconomic bias in large language models (LLMs) without relying on subjective human judgments. Unlike traditional methods, IRT accounts for item difficulty, improving ideological bias estimation. We fine-tune two LLM families (Meta-LLaMa 3.2-1B-Instruct and Chat- GPT 3.5) to represent distinct ideological positions and introduce a two-stage approach: (1) modeling response avoidance and (2) estimating perceived bias in answered responses. Our results show that off-the-shelf LLMs often avoid ideological engagement rather than exhibit bias, challenging prior claims of partisanship. This empirically validated framework enhances AI alignment research and promotes fairer AI governance.

The ability of artificial intelligence agents to make optimal decisions and generalise them to different domains and tasks is compromised in complex scenarios. One way to address this issue has focused on learning efficient representations of the world and on how the actions of agents affect them, such as disentangled representations that exploit symmetries. Whereas such representations are procedurally efficient, they are based on the compression of low-level state-action transitions, which lack structural richness. To address this problem, we propose to enrich the agent's ontology and extend the traditional conceptualisation of trajectories to provide a more nuanced view of task execution. Structurally Enriched Trajectories (SETs) extend the encoding of sequences of states and their transitions by incorporating hierarchical relations between objects, interactions and affordances. SETs are built as multi-level graphs, providing a detailed representation of the agent dynamics and a transferable functional abstraction of the task. SETs are integrated into an architecture, Structurally Enriched Trajectory Learning and Encoding (SETLE), that employs a heterogeneous graph-based memory structure of multi-level relational dependencies essential for generalisation. Using reinforcement learning as a data generation tool, we demonstrate that SETLE can support downstream tasks, enabling agents to recognise task-relevant structural patterns across diverse environments.

Comprehensive evaluations of language models (LM) during both development and deployment phases are necessary because these models possess numerous capabilities (e.g., mathematical reasoning, legal support, or medical diagnostic) as well as safety risks (e.g., racial bias, toxicity, or misinformation). The average score across a wide range of benchmarks provides a signal that helps guide the use of these LMs in practice. Currently, holistic evaluations are costly due to the large volume of benchmark questions, making frequent evaluations impractical. A popular attempt to lower the cost is to compute the average score on a subset of the benchmark. This approach, unfortunately, often renders an unreliable measure of LM performance because the average score is often confounded with the difficulty of the questions in the benchmark subset. Item response theory (IRT) was designed to address this challenge, providing a reliable measurement by careful controlling for question difficulty. Unfortunately, question difficulty is expensive to estimate. Facing this challenge, we train a model that predicts question difficulty from its content, enabling a reliable measurement at a fraction of the cost. In addition, we leverage this difficulty predictor to further improve the evaluation efficiency through training a question generator given a difficulty level. This question generator is essential in adaptive testing, where, instead of using a random subset of the benchmark questions, informative questions are adaptively chosen based on the current estimation of LLM performance. Experiments on 22 common natural language benchmarks and 172 LMs show that this approach is more reliable and efficient compared to current common practice.

Efficient deployment of deep neural networks on resource-constrained devices demands advanced compression techniques that preserve accuracy and interoperability. This paper proposes a machine learning framework that augments Knowledge Distillation (KD) with Integrated Gradients (IG), an attribution method, to optimise the compression of convolutional neural networks. We introduce a novel data augmentation strategy where IG maps, precomputed from a teacher model, are overlaid onto training images to guide a compact student model toward critical feature representations. This approach leverages the teacher's decision-making insights, enhancing the student's ability to replicate complex patterns with reduced parameters. Experiments on CIFAR-10 demonstrate the efficacy of our method: a student model, compressed 4.1-fold from the MobileNet-V2 teacher, achieves 92.5% classification accuracy, surpassing the baseline student's 91.4% and traditional KD approaches, while reducing inference latency from 140 ms to 13 ms--a tenfold speedup. We perform hyperparameter optimisation for efficient learning. Comprehensive ablation studies dissect the contributions of KD and IG, revealing synergistic effects that boost both performance and model explainability. Our method's emphasis on feature-level guidance via IG distinguishes it from conventional KD, offering a data-driven solution for mining transferable knowledge in neural architectures. This work contributes to machine learning by providing a scalable, interpretable compression technique, ideal for edge computing applications where efficiency and transparency are paramount.

We study Multimodal Large Language Models (MLLMs) with in-context learning for food preparation task planning. In this context, we identify two key challenges: cross-modal distraction and geometric feasibility. Cross-modal distraction occurs when the inclusion of visual input degrades the reasoning performance of a MLLM. Geometric feasibility refers to the ability of MLLMs to ensure that the selected skills are physically executable in the environment. To address these issues, we adapt Chain of Thought (CoT) with Self-Consistency to mitigate reasoning loss from cross-modal distractions and use affordance predictor as skill preconditions to guide MLLM on geometric feasibility. We construct a dataset to evaluate the ability of MLLMs on quantity estimation, reachability analysis, relative positioning and collision avoidance. We conducted a detailed evaluation to identify issues among different baselines and analyze the reasons for improvement, providing insights into each approach. Our method reaches a success rate of 76.7% on the entire dataset, showing a substantial improvement over the CoT baseline at 36.7%.

Large language models (LLMs) have demonstrated remarkable capabilities in various natural language processing tasks. However, achieving strong performance in specialized domains like mathematical reasoning and non-English languages often requires extensive training on massive datasets. This paper investigates a contrasting approach: strategic fine-tuning on a small, high-quality, bilingual (English-French) dataset to enhance both the reasoning capabilities and French language proficiency of a large language model. Rather than relying on scale, we explore the hypothesis that targeted data curation and optimized training can achieve competitive, or even superior, performance. We demonstrate, through targeted supervised fine-tuning (SFT) on only 2,000 carefully selected samples, significant improvements in mathematical reasoning. Specifically, Pensez 7B exhibits an increase in accuracy of the base model up to 20% on the AIME25 and a 12% increase on a French MATH level 5 benchmark. These results challenge the prevailing assumption that massive datasets are aprerequisite for strong reasoning performance in LLMs, highlighting the potential of strategic data curation and optimized fine-tuning for enhancing both specialized skills and multilingual capabilities. Our findings have implications for the efficient development of high-performing, multilingual LLMs, especially in resource-constrained scenarios.