Yalun Dai, Yangyu Huang, Tongshen Yang, Yonghan Wang, Xin Zhang, Wenshan Wu, Qihao Zhao, Hao Li, Yuanyuan Gao, Kim-Hui Yap, Scarlett Li. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Multiple-choice question (MCQ) datasets like Massive Multitask Language Understanding (MMLU) are widely used to evaluate the commonsense, understanding, and problem-solving abilities of large language models (LLMs). However, the open-source nature of these benchmarks and the broad sources of training data for LLMs have inevitably led to benchmark contamination, resulting in unreliable evaluation. To alleviate this issue, we propose the contamination-free MCQ benchmark called MMLU-CF, which reassesses LLMs’ understanding of world knowledge by averting both unintentional and malicious data contamination. To mitigate unintentional data contamination, we source questions from a broader domain of over 200 billion webpages and apply three specifically designed decontamination rules. To prevent malicious data contamination, we divide the benchmark into validation and test sets with similar difficulty and subject distributions. The test set remains closed-source to ensure reliable results, while the validation set is publicly available to promote transparency and facilitate independent evaluation. The performance gap between these two sets of LLMs will indicate the contamination degree on the validation set in the future. We evaluated over 40 mainstream LLMs on the MMLU-CF. Compared to the original MMLU, not only LLMs’ performances significantly dropped but also the performance rankings of them changed considerably. This indicates the effectiveness of our approach in establishing a contamination-free and fairer evaluation standard.

Geologic map, as a fundamental diagram in geology science, provides critical insights into the structure and composition of Earth’s subsurface and surface. These maps are indispensable in various fields, including disaster assessment, resource exploration, and civil engineering. Despite their significance, current Multimodal Large Language Models (MLLMs) often fall short in geologic map understanding. This gap is primarily due to the challenging nature of cartographic generalization, which involves handling high-resolution map, managing multiple associated components, and requiring domain-specific knowledge. To quantify this gap, we construct GeoMap-Bench, the first-ever benchmark for evaluating MLLMs in geologic map understanding, which assesses the full-scale abilities in extracting, referring, grounding, reasoning, and analyzing. To bridge this gap, we introduce GeoMap-Agent, the inaugural agent designed for geologic map understanding, which features three modules: Hierarchical Information Extraction (HIE), Domain Knowledge Injection (DKI), and Prompt-enhanced Question Answering (PEQA). Inspired by the interdisciplinary collaboration among human scientists, an AI expert group acts as consultants, utilizing a diverse tool pool to comprehensively analyze questions. Through comprehensive experiments, GeoMap-Agent achieves an overall score of 0.811 on GeoMap-Bench, significantly outperforming 0.369 of GPT-4o. Our work, emPowering gEologic mAp holistiC undErstanding (PEACE) with MLLMs, paves the way for advanced AI applications in geology, enhancing the efficiency and accuracy of geological investigations. The code and data are available at https://github.com/microsoft/PEACE.

Recently, with the development of Neural Radiance Fields and Gaussian Splatting, 3D reconstruction techniques have achieved remarkably high fidelity. However, the latent representations learnt by these methods are highly entangled and lack interpretability. In this paper, we propose a novel part-aware compositional reconstruction method, called GaussianBlock, that enables semantically coherent and disentangled representations, allowing for precise and physical editing akin to building blocks, while simultaneously maintaining high fidelity. Our GaussianBlock introduces a hybrid representation that leverages the advantages of both primitives, known for their flexible actionability and editability, and 3D Gaussians, which excel in reconstruction quality. Specifically, we achieve semantically coherent primitives through a novel attention-guided centering loss derived from 2D semantic priors, complemented by a dynamic splitting and fusion strategy. Furthermore, we utilize 3D Gaussians that hybridize with primitives to refine structural details and enhance fidelity. Additionally, a binding inheritance strategy is employed to strengthen and maintain the connection between the two. Our reconstructed scenes are evidenced to be disentangled, compositional, and compact across diverse benchmarks, enabling seamless, direct and precise editing while maintaining high quality.

Long-tail recognition is challenging because it requires the model to learn good representations from tail categories and address imbalances across all categories. In this paper, we propose a novel generative and fine-tuning framework, LTGC, to handle long-tail recognition via leveraging generated content. Firstly, inspired by the rich implicit knowledge in large-scale models (e.g., large language models, LLMs), LTGC leverages the power of these models to parse and reason over the original tail data to produce diverse tail-class content. We then propose several novel designs for LTGC to ensure the quality of the generated data and to efficiently fine-tune the model using both the generated and original data. The visualization demonstrates the effectiveness of the generation module in LTGC, which produces accurate and diverse tail data. Additionally, the experimental results demonstrate that our LTGC outperforms existing state-of-the-art methods on popular long-tailed benchmarks.

Recently, many effective methods have emerged to address the robustness problem of Deep Neural Networks (DNNs) trained with noisy labels. However, existing work on learning with noisy labels (LNL) mainly focuses on balanced datasets, while real-world scenarios usually also exhibit a long-tailed distribution (LTD). In this paper, we propose an online category-aware approach to mitigate the impact of noisy labels and LTD on the robustness of DNNs. First, the category frequency of clean samples used to rebalance the feature space cannot be obtained directly in the presence of noisy samples. We design a novel category-aware Online Joint Distribution to dynamically estimate the category frequency of clean samples. Second, previous LNL methods were category-agnostic. These methods would easily be confused with noisy samples and tail categories’ samples under LTD. Based on this observation, we propose a Harmonizing Factor strategy to exploit more information from the category-aware online joint distribution. This strategy provides more accurate estimates of clean samples between noisy samples and samples with tail categories. Finally, we propose Dynamic Cost-sensitive Learning, which utilizes the loss and category frequency of the estimated clean samples to address both LNL and LTD. Compared to extensive state-of-the-art methods, our strategy consistently improves the generalization performance of DNNs on several synthetic datasets and two real-world datasets.

Recently, multi-expert methods have led to significant improvements in long-tail recognition (LTR). We summarize two aspects that need further enhancement to contribute to LTR boosting: (1) More diverse experts: (2) Lower model variance. However, the previous methods didn’t handle them well. To this end, we propose More Diverse experts with Consistency Self-distillation (MDCS) to bridge the gap left by earlier methods. Our MDCS approach consists of two core components: Diversity Loss (DL) and Consistency Self-distillation (CS). In detail, DL promotes diversity among experts by controlling their focus on different categories. To reduce the model variance, we employ KL divergence to distill the richer knowledge of weakly augmented instances for the experts’ self-distillation. In particular, we design Confident Instance Sampling (CIS) to select the correctly classified instances for CS to avoid biased/noisy knowledge. In the analysis and ablation study, we demonstrate that our method compared with previous work can effectively increase the diversity of experts, significantly reduce the variance of the model, and improve recognition accuracy. Moreover, the roles of our DL and CS are mutually reinforcing and coupled: the diversity of experts benefits from the CS, and the CS cannot achieve remarkable results without the DL. Experiments show our MDCS outperforms the state-of-the-art by 1% ~ 2% on five popular long-tailed benchmarks, including CIFAR10-LT, CIFAR100-LT, ImageNet-LT, Places-LT, and iNaturalist 2018. The code is available at https://github.com/fistyee/MDCS

Learning deep neural network (DNN) classifier with noisy labels is a challenging task because the DNN can easily overfit on these noisy labels due to its high capability. In this paper, we present a very simple but effective training paradigm called P-DIFF, which can train DNN classifiers but obviously alleviate the adverse impact of noisy labels. Our proposed probability difference distribution implicitly reflects the probability of a training sample to be clean, then this probability is employed to re-weight the corresponding sample during the training process. P-DIFF can also achieve good performance even without prior-knowledge on the noise rate of training samples. Experiments on benchmark datasets also demonstrate that P-DIFF is superior to the state-of-the-art sample selection methods.