Katelyn X. Mei, Yi-Li Hsu, Minjoon Choi, Zongwan Cao, Chenjun Xu, Bingbing Wen, Su Lin Blodgett, Lucy Lu Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

As LLM-based computer-use agents (CUAs) begin to autonomously interact with real-world interfaces, understanding their vulnerability to manipulative interface designs becomes increasingly critical. We introduce SusBench, an online benchmark for evaluating the susceptibility of CUAs to UI dark patterns, designs that aim to manipulate or deceive users into taking unintentional actions. Drawing nine common dark pattern types from existing taxonomies, we developed a method for constructing believable dark patterns on real-world consumer websites through code injections, and designed 313 evaluation tasks across 55 websites. Our study with 29 participants showed that humans perceived our dark pattern injections to be highly realistic, with the vast majority of participants not noticing that these had been injected by the research team. We evaluated five state-of-the-art CUAs on the benchmark. We found that both human participants and agents are particularly susceptible to the dark patterns of Preselection, Trick Wording, and Hidden Information, while being resilient to other overt dark patterns. Our findings inform the development of more trustworthy CUAs, their use as potential human proxies in evaluating deceptive designs, and the regulation of an online environment increasingly navigated by autonomous agents.

Spurious correlations occur when models rely on non-essential features that coincidentally co-vary with target labels, leading to incorrect reasoning under distribution shift. We consider spurious correlations in multi-modal Large Vision Language Models (LVLMs) pretrained on extensive and diverse datasets without explicit task supervision. We develop a benchmark by sourcing GPT-4o errors on real-world visual-question-answering (VQA) benchmarks, then curating a subset through LVLM-human annotation and synthetic counterfactual evaluation to identify errors caused by spurious correlations. This process yields SpuriVerse, a novel benchmark comprised of 124 distinct types of spurious correlations extracted from real-world datasets, each containing 1 realistic and 10 synthetic VQA samples for a total of 1364 multiple choice questions. We evaluate 15 open and closed-source LVLMs on SpuriVerse, finding that even state-of-the-art closed-source models struggle significantly, achieving at best only 35.0\% accuracy. Fine-tuning on synthetic examples that emphasize the spurious correlation improves performance to 78.4\%, suggesting that training on diverse spurious patterns generalizes to unseen situations: models appear to learn to avoid "shortcuts" and attend to the overall image context.

Abstract Abstention, the refusal of large language models (LLMs) to provide an answer, is increasingly recognized for its potential to mitigate hallucinations and enhance safety in LLM systems. In this survey, we introduce a framework to examine abstention from three perspectives: the query, the model, and human values. We organize the literature on abstention methods, benchmarks, and evaluation metrics using this framework, and discuss merits and limitations of prior work. We further identify and motivate areas for future research, such as whether abstention can be achieved as a meta-capability that transcends specific tasks or domains, and opportunities to optimize abstention abilities in specific contexts. In doing so, we aim to broaden the scope and impact of abstention methodologies in AI systems.1

Our paper aims to generate diverse and realistic ani-mal motion sequences from textual descriptions, without a large-scale animal text-motion dataset. While the task of text-driven human motion synthesis is already extensively studied and benchmarked, it remains challenging to transfer this success to other skeleton structures with limited data. In this work, we design a model architecture that imitates Generative Pretraining Transformer (GPT), utilizing prior knowledge learned from human data to the animal domain. We jointly train motion autoencoders for both animal and human motions and at the same time optimize through the similarity scores among human motion encoding, animal motion encoding, and text CLIP embedding. Presenting the first solution to this problem, we are able to generate animal motions with high diversity and fidelity, quantitatively and qualitatively outperforming the results of training human motion generation baselines on animal data. Additionally, we introduce AnimalML3D, the first text-animal motion dataset with 1240 animation sequences spanning 36 different ani-mal identities. We hope this dataset would mediate the data scarcity problem in text-driven animal motion generation, providing a new playground for the research community.

Learning multi-organ segmentation from multiple partially-labeled datasets attracts increasing attention. It can be a promising solution for the scarcity of large-scale, fully labeled 3D medical image segmentation datasets. However, existing algorithms of multi-organ segmentation on partially-labeled datasets neglect the semantic relations and anatomical priors between different categories of organs, which is crucial for partially-labeled multi-organ segmentation. In this paper, we tackle the limitations above by proposing the Cross-Class Query Network (CCQ). CCQ consists of an image encoder, a cross-class query learning module, and an attentive refinement segmentation module. More specifically, the image encoder captures the long-range dependency of a single image via the transformer encoder. Cross-class query learning module first generates query vectors that represent semantic concepts of different categories and then utilizes these query vectors to find the class-relevant features of image representation for segmentation. The attentive refinement segmentation module with an attentive skip connection incorporates the high-resolution image details and eliminates the class-irrelevant noise. Extensive experiment results demonstrate that CCQ outperforms all the state-of-the-art models on the MOTS dataset, which consists of seven organ and tumor segmentation tasks. Code is available at https://github.com/Yang-007/CCQ.git.

Many information access and machine learning systems, including recommender systems, lack transparency and accountability. High-quality recommendation explanations are of great significance to enhance the transparency and interpretability of such systems. However, evaluating the quality of recommendation explanations is still challenging due to the lack of human-annotated data and benchmarks. In this paper, we present a large explanation dataset named RecoExp, which contains thousands of crowdsourced ratings of perceived quality in explaining recommendations. To measure explainability in a comprehensive and interpretable manner, we propose ExpScore, a novel machine learning-based metric that incorporates the definition of explainability from various perspectives (e.g., relevance, readability, subjectivity, and sentiment polarity). Experiments demonstrate that ExpScore not only vastly outperforms existing metrics and but also keeps itself explainable. Both the RecoExp dataset and open-source implementation of ExpScore will be released for the whole community. These resources and our findings can serve as forces of public good for scholars as well as recommender systems users.