text string | source string |
|---|---|
pair. We tested different templates and chose the ones that resulted in the highest classification accuracy. Each prompt was designed 14 Table 4: Classification performance of the models across the datasets. Except for LLAMA3.1 1B on the sentiment classification datasets, where it always predicts positive sentiment, th... | https://arxiv.org/abs/2505.17630v1 |
the camera-ready version. 0.0 2.5 5.0 7.5 10.0 12.5 15.0 Layer0.00.20.40.6→ ComprehensivenessAttribution Patching Integrated Gradients ATP* GIM 0.0 2.5 5.0 7.5 10.0 12.5 15.0 Layer0.00.20.40.6← SufficiencyAttribution Patching Integrated Gradients ATP* GIM (a) Twitter 0.0 2.5 5.0 7.5 10.0 12.5 15.0 Layer0.00.20.40.6→ Comp... | https://arxiv.org/abs/2505.17630v1 |
0.82 0.73 0.16 0.26 0.31 0.13 0.45 1.5 0.58 0.70 0.78 0.84 0.75 0.12 0.18 0.28 0.23 0.38 2 0.60 0.71 0.78 0.83 0.76 0.11 0.19 0.30 0.17 0.31 2.5 0.58 0.70 0.78 0.84 0.75 0.12 0.18 0.28 0.23 0.38 3 0.60 0.71 0.78 0.80 0.71 0.11 0.20 0.30 0.16 0.32 5 0.60 0.71 0.76 0.82 0.72 0.11 0.21 0.32 0.28 0.31 10 0.60 0.71 0.75 0.7... | https://arxiv.org/abs/2505.17630v1 |
(b) Fever 0 5 10 15 20 25 Layer0.00.20.40.60.8→ ComprehensivenessAttribution Patching Integrated Gradients ATP* GIM 0 5 10 15 20 25 Layer0.00.20.40.60.8← SufficiencyAttribution Patching Integrated Gradients ATP* GIM (c) Movie review 0 5 10 15 20 25 Layer0.00.20.40.6→ ComprehensivenessAttribution Patching Integrated Gradi... | https://arxiv.org/abs/2505.17630v1 |
David C. Wyld et al. (Eds): Signal, CDKP, AdNLP, MLT, SAI – 2025 pp. 27-39, 2025. CS & IT - CSCP 2025 DOI: 10.5121/csit.2025.150903 SURFACING SEMANTIC ORTHOGONALITY ACROSS MODEL SAFETY BENCHMARKS : A MULTI -DIMENSIONAL ANALYSIS Jonathan Bennion 1, Shaona Ghosh 2, Mantek Singh 3, Nouha Dziri 4 1 The Objective AI, USA 2 ... | https://arxiv.org/abs/2505.17636v1 |
jailbreaks, and cultural contexts [10]. BeaverTails aligns human preferences within a 14 -category safety taxonomy to enhance ethical alignment of LLMs [11]. GretelAI uniquely focuses on evaluating synthetic data generation with privacy guarantees, emphasizing statistical fidelity while preserving differential privacy ... | https://arxiv.org/abs/2505.17636v1 |
past research methods [17], assuming 15 clusters to align with the 12 core harm categories from Aegis 2.0 [9], plus 20 percent for broader semantic coverage [18]. This is illustrated in Eq uation 2, with kmax= 15 clusters and b = 5 benchmarks. ntotal= (max(nkmeans ) × (kmax× 1.2) × b) (2) Assumptions for this sample si... | https://arxiv.org/abs/2505.17636v1 |
with a long tail extending for a smaller number of prompts over 2500 characters. 3.2. Embedding Model Comparison MiniLM and MPNet excel in di fferent tasks, while similar in size, and were good candidates to use in this analysis for comparison [7] in a rigorous analysis. MiniLM provides fast, efficient embeddings with ... | https://arxiv.org/abs/2505.17636v1 |
dimensional importance and accommodates anisotropic clusters [31]. This facilitates the inclusion of diverse semantic relationships, length variations, and potential semanti c outliers, commonly seen in jailbreak attempts and adversarial prompting strategies [2]. 𝑑𝑀(𝑥,𝑦)= √(𝑥−𝑦)𝑇Σ−1(𝑥−𝑦) (6) Since the later di... | https://arxiv.org/abs/2505.17636v1 |
k provide insight into intra -cluster cohesion for individual data points, the elbow method focuses on the overall within -cluster sum of squares, calculated [36] in Equation 8 below, where Wkis the sum of squares within clusters. (8) The convergence of both elbow and silhouette methods near k=6 (Figure 5) confirms tha... | https://arxiv.org/abs/2505.17636v1 |
nuanced real -world scenarios [38]. This divergence in prompt design likely reflects differing safety assessment approaches: shorter prompts target specific vulnerabili ties, while longer ones evaluate model behavior in nuanced, real -world scenarios [38]. Fig.7. Kernel density distribution of prompt lengths across fiv... | https://arxiv.org/abs/2505.17636v1 |
Khoja, A., Gatti, A., Phan, L., Yin, X., et al. (2024) ”Safetywashing: Do AI Safety Benchmarks ActuallyMeasure Safety Progress?”, arXiv preprint arXiv:2405.19928. [6] Lee, N., Hong, J., & Thorne, J. (2025) ”Evaluating the Consistency of LLM Evaluators”, Proceedings of the 31st Inte rnational Conference on Computational... | https://arxiv.org/abs/2505.17636v1 |
pp. 1 -14. [26] Wang, Y ., Huang, H., Rudin, C., &Shaposhnik, Y . (2021). Understanding how dimension reduction tools work: An empirical approach to deciphering t -SNE, UMAP, TriMap, and PaCMAP for data visualization. Journal of Machine Learning Research, 22, 1 -73. [27] Bergstra, J. , & Bengio, Y . (2012). ”Random sea... | https://arxiv.org/abs/2505.17636v1 |
Stereotype Detection in Natural Language Processing ALESSANDRA TERESA CIGNARELLA, Language and Translation Technology Team, Ghent University, Belgium ANASTASIA GIACHANOU, Department of Methodology and Statistics, Utrecht University, The Netherlands ELS LEFEVER, Language and Translation Technology Team, Ghent University... | https://arxiv.org/abs/2505.17642v1 |
specific permission and/or a fee. Request permissions from permissions@acm.org. ©2025 Copyright held by the owner/author(s). Publication rights licensed to ACM. Manuscript submitted to ACM Manuscript submitted to ACM 1 2 Cignarella et al. sexual orientation, leading to polarization, radicalization and violence. While v... | https://arxiv.org/abs/2505.17642v1 |
provide different levels of care to patients based on their race, often offering less pain relief to black patients compared to white patients, despite similar reported pain levels.2 A well-known method to measure implicit bias is the Implicit Association Test (IAT), a widely used tool in social cognition research to m... | https://arxiv.org/abs/2505.17642v1 |
theoretical papers that cover a sociological perspective of the problem. Stereotype detection is a rather new field in NLP and computational linguistics, and as explained before, is closely related to the fields of bias and hate speech detection. In particular, although gender bias has been researched to a great extent... | https://arxiv.org/abs/2505.17642v1 |
stereotypes as recurrent, socially constructed (generalized) associations that ascribe fixed characteristics to individuals based on their group membership. These associations often simplify complex realities, reinforcing bias and prejudices and limiting freedom and opportunities for those subjected to them. Stereotypi... | https://arxiv.org/abs/2505.17642v1 |
faced in this field, including limitations in data, evaluation metrics, and language coverage. Finally, Section 5 concludes the survey by summarizing the insights gained and outlining future research directions, with Section 5.1 highlighting specific opportunities for advancing stereotype detection in NLP. 2 WHAT NLP R... | https://arxiv.org/abs/2505.17642v1 |
the data’s consistency and reliability (see Section 2.1.2). However, before proceeding with an extreme step of filtering, we aimed to identify the main research topics that present a significant overlap with the terms < stereotype detection > in the papers we collected. To achieve this, we applied BERTopic9on the 6,304... | https://arxiv.org/abs/2505.17642v1 |
stereotyped > or < stereotyping >AND <nlp> or < natural language processing > appeared in the title ORin the abstract. This ensured the dataset remained focused on the topic of Stereotype Detection in NLP . The final count amounts to 139papers . 2.1.3 Analyses .The analyses that follow are thus carried out on the final... | https://arxiv.org/abs/2505.17642v1 |
Processing (GeBNLP). Venue N# papers arXiv.org 21 Annual Meeting of the Association for Computational Linguistics (ACL) 11 Conference on Empirical Methods in Natural Language Processing (EMNLP) 8 North American Chapter of the Association for Computational Linguistics (NAACL) 6 International Conference on Language Resou... | https://arxiv.org/abs/2505.17642v1 |
spreading irony and stereotypes towards immigrants, women and LGBT+ people. Similarly, other repositories belong to participants of the 2024 shared task “DETESTS-Dis” organized at IberLEF in 2024, to detect and classify explicit and implicit stereotypes in texts from social media and comments on news articles in Spanis... | https://arxiv.org/abs/2505.17642v1 |
et al.[2022]; Chang et al .[2019]; Davani et al .[2023]; Kurita et al .[2019]; Liang et al .[2020]; Nadeem et al . [2021]; Nozza et al .[2021]; Pujari et al .[2022]; Ranaldi et al.[2024]; Shaikh et al .[2023]; Shen et al .[2021]; Sun et al.[2019]; Ungless et al .[2022]; Vargas et al .[2023]; Zhou et al. [2023]; Zmigrod... | https://arxiv.org/abs/2505.17642v1 |
Extends stereotype content research by introducing the ABC model, which cat- egorizes stereotypes along three dimensions: Agency (socioeconomic success), Beliefs (conservative-progressive ideology), and Communion (warmth and trust- worthiness).Stereotypes across different so- cial groups, such as race, gen- der, and po... | https://arxiv.org/abs/2505.17642v1 |
are universal. Another theoretical contribution was made by Nicolas et al .[2022], who explored how stereotypes form in different Manuscript submitted to ACM Stereotype Detection in Natural Language Processing 13 contexts, developing a taxonomy of stereotypes and demonstrating that they can emerge in various social and... | https://arxiv.org/abs/2505.17642v1 |
of detecting biases that are not overtly expressed. The intersection of bias detection with hate speech, offensiveness, and stance analysis is also evident in datasets like Queereotypes ,HaSpeeDe2 , and StereoImmigrants . The datasets focus on various biases, stereotypes, and discriminatory content across multiple doma... | https://arxiv.org/abs/2505.17642v1 |
investigate and quantify the social biases that emerge in natural language inference data as a result of the human elicitation process.Social bias across various targets. [Mendelsohn et al. 2020] English The main goal of this paper is to propose a systematic, computational framework that al- lows researchers to analyze... | https://arxiv.org/abs/2505.17642v1 |
work sheds some light on the importance of data selection for our understanding of societal stereotypes, emphasizing the need for context-aware models that account for data-source-variations in stereotype manifestations. Manuscript submitted to ACM 16 Cignarella et al. Another work that includes ChatGPT for studying bi... | https://arxiv.org/abs/2505.17642v1 |
role in measuring and evaluating biases in NLP models. For instance, Nadeem et al .[2021] introduce StereoSet, a dataset specifically designed to assess stereotypical biases in pretrained language models across gender, profession, race, and religion using the Context Association Test. These evaluations Manuscript submi... | https://arxiv.org/abs/2505.17642v1 |
bias in hate speech classification systems, particularly in English and Portuguese datasets from social media platforms. Additionally, Shaikh et al .[2023] explore the effects of zero-shot Chain of Thought (CoT) prompting in large language models, demonstrating that CoT often exacerbates bias and toxicity in model outp... | https://arxiv.org/abs/2505.17642v1 |
al .[2024a] extends the analysis to Italian, Spanish, and French, using GilBERTo, BETO, and CamemBERT, with the best macro F1 scores reaching 0.805 (Italian), 0.826 (Spanish), and 0.716 (French). For Spanish, Sánchez-Junquera et al .[2021] explores several transformer models, including M-BERT, XLM-RoBERTa, BETO, and Sp... | https://arxiv.org/abs/2505.17642v1 |
Definitions and Theoretical Frameworks Throughout our survey of over 50+ papers on stereotype detection in NLP, we observed a general consensus on the definition of stereotypes. Most studies align with the foundational work of social psychologists such as Fiske et al . [2002] and Koch et al .[2016], whose frameworks do... | https://arxiv.org/abs/2505.17642v1 |
problem as part of a broader task, such as hate speech detection [Cignarella et al .2024; Sanguinetti et al .2020]. The datasets may vary in terms of the source/type of textual data, size, language, phenomenon, etc. •Source / Type. The choice of data types is a very important factor in effectively measuring and mitigat... | https://arxiv.org/abs/2505.17642v1 |
HaSpeeDe2 [Sanguinetti et al . 2020]. The inclusion of datasets dedicated to the LGBTQIA+ community, such as Queereotypes [Cignarella et al .2024], demonstrates the growing awareness of biases affecting marginalized social groups beyond traditional categories like gender and race. •Language and geographical focus. We o... | https://arxiv.org/abs/2505.17642v1 |
judgment. Notably, there are datasets with no explicit annotation or cases where annotation details are unclear or not always specified. One dataset creation involved 89 annotators from 16 different countries, demonstrating a commitment to linguistic and regional diversity [Jha et al .2023]. Overall, the annotation str... | https://arxiv.org/abs/2505.17642v1 |
underrepresented in stereotype and bias-related studies. While the dataset includes Tamil and code-mixed Tamil-English [Chakravarthi et al .2022], such instances remain isolated rather than part of a broader effort to engage with underrepresented linguistic groups. Regarding national perspectives, relatively few papers... | https://arxiv.org/abs/2505.17642v1 |
detection models are evaluated using static datasets, which fail to capture the evolving nature of stereotypes, biases, and societal attitudes over time. For example, datasets collected several years ago may no longer reflect current lin- guistic trends or emerging biases, making them less effective for evaluating cont... | https://arxiv.org/abs/2505.17642v1 |
Alternative Stereotype Models. Current stereotype detection frameworks largely rely on predefined taxonomies, but alternative models may offer deeper insights into how stereotypes manifest in language. Davani et al . [2023] propose the Agent-Beliefs-Communion (ABC) model as a more structured way to analyze stereotypes,... | https://arxiv.org/abs/2505.17642v1 |
Agency and communion from the perspective of self versus others. Journal of Personality and Social Psychology 93, 5 (2007), 751–763. https://doi.org/10.1037/0022-3514.93.5.751 Martha Augoustinos and Iain Walker. 1998. The construction of stereotypes within social psychology: From social cognition to ideology. Theory & ... | https://arxiv.org/abs/2505.17642v1 |
Homophobia and Transphobia? Experiments in a multilingual code-mixed setting for social media governance. International Journal of Information Management Data Insights 2, 2 (2022), 100119. Kai-Wei Chang, Vinodkumar Prabhakaran, and Vicente Ordonez. 2019. Bias and fairness in Natural Language Processing. In Proceedings ... | https://arxiv.org/abs/2505.17642v1 |
follow from perceived status and competition. Journal of Personality and Social Psychology (2002), 878–902. Paula Fortuna and Sérgio Nunes. 2018. A Survey on Automatic Detection of Hate Speech in Text. ACM Computing Surveys (CSUR) 51 (2018), 1–30. https://api.semanticscholar.org/CorpusID:52184457 Kathleen C. Fraser, Sv... | https://arxiv.org/abs/2505.17642v1 |
the association for computational linguistics: Human language technologies . 3598–3609. Shahar Levy, Koren Lazar, and Gabriel Stanovsky. 2021. Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation. InFindings of the Association for Computational Linguistics: EMNLP 2021 . 2470–2... | https://arxiv.org/abs/2505.17642v1 |
Shrimai Prabhumoye, Brendon Boldt, Ruslan Salakhutdinov, and Alan W Black. 2021. Case Study: Deontological Ethics in NLP. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies . Association for Computational Linguistics, Online,... | https://arxiv.org/abs/2505.17642v1 |
Aili Shen, Xudong Han, Trevor Cohn, Timothy Baldwin, and Lea Frermann. 2021. Contrastive Learning for Fair Representations. https://doi.org/10. 48550/arXiv.2109.10645 arXiv:2109.10645 [cs]. Manuscript submitted to ACM Stereotype Detection in Natural Language Processing 29 Karolina Stańczak and Isabelle Augenstein. 2021... | https://arxiv.org/abs/2505.17642v1 |
arXiv:2505.17643v1 [cs.CL] 23 May 2025Bridging Electronic Health Records and Clinical Texts: Contrastive Learning for Enhanced Clinical Tasks Sara Ketabi Vector Institute, University of Toronto, The Hospital for Sick Children Dhanesh Ramachandram Vector Institute Abstract Conventional machine learning models, particula... | https://arxiv.org/abs/2505.17643v1 |
Ji et al. (2021), to improve the performance of downstream clinical tasks. While these approaches have demonstrated significant potential in image-text settings, there has been relatively limited exploration of CL applied to other clinical modalities. In particular, the integration of EHR with unstructured textual data... | https://arxiv.org/abs/2505.17643v1 |
learning capabilities of DL frameworks. Such frameworks can integrate EHR data with free-text input, enabling more semantically rich EHR representations. 2 2.2 Multimodal Contrastive Learning Frameworks Multimodal CL frameworks have achieved remarkable success in integrating various modalities of input data and learnin... | https://arxiv.org/abs/2505.17643v1 |
a self-supervised masked feature reconstruction task. This pretraining stage enables the model to capture internal dependencies and useful patterns within the EHR modality. To enhance the training stability and efficiency, we froze the initial embedding and feature-splitting layers of TabNet. These layers are believed ... | https://arxiv.org/abs/2505.17643v1 |
fine-tuning, assessing the impact of transferring cross-modal semantic knowledge from clinical notes into structured EHR representations. The architecture used for fine-tuning the downstream tasks can be observed in Figure 2. 4 Figure 1: The Proposed EHR-Text CL Framework: EHR is encoded with TabNet initialized with ma... | https://arxiv.org/abs/2505.17643v1 |
transform these encoded values into dense vectorized representations, enabling the model to capture semantic relationships between feature categories. For the text data, we standardized all discharge summaries by converting them into lowercase. We also removed all dates, numbers, additional spaces, and punctuation mark... | https://arxiv.org/abs/2505.17643v1 |
respectively. Moreover, to assess the statistical significance of performance differences, we conducted two-tailed t-tests on the AUC scores obtained across the five seeds. The detailed results of these tests are presented in the supplementary material. 4.5 Hospital Readmission Prediction Table 1: Mean Test AUC Results... | https://arxiv.org/abs/2505.17643v1 |
also is able to incorporate new semantic information efficiently during fine-tuning. Freezing the embedding and initial splitting layers during downstream fine-tuning helped retain generalized feature patterns learned through pretraining, while allowing the deeper layers to adjust to the target task. The framework’s st... | https://arxiv.org/abs/2505.17643v1 |
clinical workflow and patient outcomes. 9 References Sercan ¨O Arik and Tomas Pfister. Tabnet: Attentive interpretable tabular learning. In Proceedings of the AAAI conference on artificial intelligence , volume 35, pages 6679–6687, 2021. Iz Beltagy, Matthew E Peters, and Arman Cohan. Longformer: The long-document trans... | https://arxiv.org/abs/2505.17643v1 |
Ren, Brooke Armfield, Tezcan Ozrazgat-Baslanti, Jeremy A Balch, et al. Global contrastive training for multimodal electronic health records with language supervision. arXiv preprint arXiv:2404.06723 , 2024b. 10 Sergei Popov, Stanislav Morozov, and Artem Babenko. Neural oblivious decision ensembles for deep learning on ... | https://arxiv.org/abs/2505.17643v1 |
arXiv:2505.17645v1 [cs.CV] 23 May 2025HoloLLM: Multisensory Foundation Model for Language-Grounded Human Sensing and Reasoning Chuhao Zhou1, Jianfei Yang1∗ 1MARS Lab, Nanyang Technological University {chuhao002@e, jianfei.yang}@ntu.edu.sg Project Page: https://chuhaozhou99.github.io/HoloLLM Abstract Embodied agents ope... | https://arxiv.org/abs/2505.17645v1 |
modalities into an MLLM is non-trivial due to two key challenges. First, we must align sensing modalities with text using limited training data. For common modalities such as RGB or depth images, millions of web-sourced ‘modality-text’ data pairs are available [ 12–14], which enable large-scale pre-training of multimod... | https://arxiv.org/abs/2505.17645v1 |
deal with the data-scarce feature learning and modality-text alignment, respectively. •To evaluate HoloLLM, we design a human-VLM collaborative data curation pipeline to construct the text-paired multimodal dataset. Then, the first multisensory benchmark for human sensing is established with different settings and base... | https://arxiv.org/abs/2505.17645v1 |
LLM LLM (·,·), which takes Zmand the text tokens Ztextcorresponding to human instructions as 3 Figure 2: Architecture of HoloLLM. Given multimodal inputs Xm, HoloLLM utilizes modality- specific tokenizers and a universal encoder to extract pre-aligned initial embeddings Ym CLIP . Mean- while, pre-trained tailored encod... | https://arxiv.org/abs/2505.17645v1 |
identifies the text-aligned modality features from Vmand injects them into the queries Qmfor enhancement. The updated queries are projected into the text space via the feedforward layer, which serves as enhanced queries for the next block. Finally, the multimodal tokens from the last block Zm=MLP (Qm L)can be aligned w... | https://arxiv.org/abs/2505.17645v1 |
data. As shown in Fig. 4, we take the MM-Fi dataset as an example to illustrate our data curation pipeline; more details can be found in Appendix A. Action QA generation. In this work, Action QA is conditioned on options. To ensure precision and diversity, 5 questions are first annotated by human experts and rewritten ... | https://arxiv.org/abs/2505.17645v1 |
2.6 1.9 2.4 8.9 8.9 8.9 8.9 8.9 8.9 Honeybee CVPR’24 Proj 2.3 2.5 2.0 1.7 2.0 2.1 10.0 10.0 10.1 10.3 10.2 10.1 OneLLM CVPR’24 Proj 3.6 3.5 4.7 3.5 4.2 3.9 15.5 15.3 13.3 15.9 16.6 15.3 ImageBind CVPR’23 Enc 89.3 76.7 45.8 11.1 8.0 46.2 28.4 21.2 18.8 16.2 14.8 19.9 HoloLLM - Proj 99.8 99.7 95.8 84.2 52.8 86.5 30.8 31.... | https://arxiv.org/abs/2505.17645v1 |
The Accuracy (%) and METEOR (%) are adopted for Action QA and Caption, respectively 4.2 Main Results We compare HoloLLM with state-of-the-art MLLMs across three tasks: Action QA, Action Caption, and Action Recognition. Specifically, we divided existing methods into Encoder-based (Image- Bind [ 31]) and Projector-based ... | https://arxiv.org/abs/2505.17645v1 |
4.5 12.8 19.8 14.7 17.1 10.8 13.7 15.2 Table 3: Ablations results. We conduct experiments on both MM-Fi and XRF55 under “Cross- Environment” setting to show the contribution of the key components. 4.3 Ablation Results We conduct the ablation study on both MM-Fi and XRF55 datasets under the “CrossEnv” setting to show th... | https://arxiv.org/abs/2505.17645v1 |
Qualitative Results. We give some qualitative results of HoloLLM in the “CrossEnv” setting in Fig. 7. These results show that HoloLLM can perform Action QA and Action Caption tasks across sensing modalities in diverse environments. More results and analysis are detailed in Appendix C. 5 Conclusion and Limitations In th... | https://arxiv.org/abs/2505.17645v1 |
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages 20502–20512, 2022. [10] Fei Wang, Yizhe Lv, Mengdie Zhu, Han Ding, and Jinsong Han. Xrf55: A radio frequency dataset for human indoor action analysis. ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies , 8(1):1–34, 2024. [11] Ji... | https://arxiv.org/abs/2505.17645v1 |
for 3d human body reconstruction in all weather conditions. In IEEE International Conference on Robotics and Automation (ICRA) , pages 2752–2758, 2023. [24] Haoxuan Qu, Yujun Cai, and Jun Liu. Llms are good action recognizers. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages 18395–18406,... | https://arxiv.org/abs/2505.17645v1 |
Mo, and Leonidas J Guibas. Pointnet: Deep learning on point sets for 3d classification and segmentation. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages 652–660, 2017. [39] Laurens Van der Maaten and Geoffrey Hinton. Visualizing data using t-sne. Journal of Machine Learning Research , 9... | https://arxiv.org/abs/2505.17645v1 |
is shown in Fig. 11 (a). Consequently, for the remaining data samples in both datasets, we adopt LLaV A-Video [ 26] to automatically generate captions through in-context learning. As illustrated in Fig. 12, for a specific data sample s, we first build the prompting message by progressively integrating the ‘system promp... | https://arxiv.org/abs/2505.17645v1 |
in Tab. 4. B.3 Training Details The AdamW optimizer with β1= 0.9,β2= 0.95, and weight decay of 0.1 is adopted in our training. For stage one, we utilize the training set of the corresponding experimental setting (Random, CrossSub, CrossEnv) to pretrain the tailored encoders for 120 epochs on a single A100 GPU. The lear... | https://arxiv.org/abs/2505.17645v1 |
action recognition tasks for almost all modalities. For certain sensing modalities, comparable performances are observed under the “CrossSub” and “CrossEnv” settings. In fact, some sensing modalities are sensitive to different subjects and scenarios. Enhancing the generalization capability of sensing modalities toward ... | https://arxiv.org/abs/2505.17645v1 |
EV ADE: Multimodal Benchmark for Evasive Content Detection in E-Commerce Applications Ancheng Xu1,2∗Zhihao Yang2,3∗Jingpeng Li5Guanghu Yuan1Longze Chen1,2 Liang Yan5Jiehui Zhou5Zhen Qin5Hengyun Chang5 Hamid Alinejad-Rokny4Bo Zheng5†Min Yang1† 1Shenzhen Key Laboratory for High Performance Data Mining, Shenzhen Institute... | https://arxiv.org/abs/2505.17654v1 |
is N.” (Partial Match ) o1mini: “Let’s think step by step ... the conclusion is B.” (Partial Match )Adversarial operationPixelateZH:专攻失眠焦虑抑郁EN:Specialized in insomnia, anxiety, and depression. Weight Loss ProductsText Input Image Input Ground-Truth: A, C GPT4o: “Let’s think step by step, look at the content of the pict... | https://arxiv.org/abs/2505.17654v1 |
evaluating how well LLMs and VLMs detect evasive content in real-world e-commerce scenarios. Every example is iteratively 2 annotated by domain experts to ensure accurate and consistent ground truth. EV ADE contains 2,833 text samples and 13,961 product images, collected from six demanding product categories where dece... | https://arxiv.org/abs/2505.17654v1 |
GPT-4V misclassified over one-third of unsafe and over half of safe inputs, exposing poor safety awareness across 29 threats. VLDBench [ 37] evaluated 31,000 news-image pairs and showed that adding visual context improves disinformation detection by 5–35% and enhances compliance monitoring. 3 2.3 Gap and Our Contributi... | https://arxiv.org/abs/2505.17654v1 |
on six rule prompts. Predictions from three LLMs (GPT-o1mini, DeepSeek-R1, QwenMax) and three VLMs (GPT-4o, Claude-3.7, Gemini-2.5- 4 Pro) were then used to identify samples that diverged from human judgment. These discrepant cases were flagged for re-annotation by professional annotators in the second and third rounds... | https://arxiv.org/abs/2505.17654v1 |
purpose of this approach is to allow models for free reasoning based on the prompt, in order to explore the upper and lower bounds of its performance. 2.Detailed Instruction refers to the approach where, in the input prompt, we not only include the necessary special keywords but also introduce positive and negative exa... | https://arxiv.org/abs/2505.17654v1 |
of both LLMs and VLMs is generally suboptimal, with substantial variability across models. As shown in Table 3 and Table 10, the closed- source model Gemini-2.5-pro consistently achieves the highest accuracy across the six violation categories, followed closely by Qwen-VL-Max . Among open-source VLMs, Qwen2.5-VL-72B pe... | https://arxiv.org/abs/2505.17654v1 |
understand how models behave under longer context and clearer taxonomy, where ambiguous overlaps between categories are removed, we turn to the results from the All-in-One task. 5.2 All-in-One Results In the All-in-One task, we observe substantial performance improvements across many models, especially for smaller LLMs... | https://arxiv.org/abs/2505.17654v1 |
the left of the slash indicate partial accuracy, while those to the right indicate full accuracy. Model-Flat Simplified. Detailed. Model-Think Simplified. Detailed. Qwen-3-32B 57.11 /52.84 55.54 / 50.71 Qwen-3-32B (think) 58.56 /53.44 55.94 / 50.73 Qwen-3-30B-A3B 55.07 / 50.58 54.39 / 50.55 Qwen-3-30B-A3B (think) 56.64... | https://arxiv.org/abs/2505.17654v1 |
deployments. Although EV ADE is a multi-class task, it includes an implicit rule: "Z. other" (no violation) cannot be selected alongside any regulated category. Some weaker models violate this constraint by labeling items as both compliant and non-compliant, revealing poor rule comprehension and instruction- following ... | https://arxiv.org/abs/2505.17654v1 |
their work, particularly in applications that may affect individuals or communities. References [1] Alibaba. Qwen3. https://qwenlm.github.io/blog/qwen3// , 2025. 10 [2] Alibaba. Qwen-vl-max. https://huggingface.co/spaces/Qwen/Qwen-VL-Max/ , 2025. [3]M. Altakrori, T. Scialom, B. C. M. Fung, and J. C. K. Cheung. A multif... | https://arxiv.org/abs/2505.17654v1 |
Chen, S. Ye, S. Wang, S. Yu, S. Zhou, S. Pan, S. S. Li, S. Zhou, S. Wu, S. Ye, T. Yun, T. Pei, T. Sun, T. Wang, W. Zeng, W. Zhao, W. Liu, W. Liang, W. Gao, W. Yu, W. Zhang, W. L. Xiao, W. An, X. Liu, X. Wang, X. Chen, X. Nie, X. Cheng, X. Liu, X. Xie, X. Liu, X. Yang, X. Li, X. Su, X. Lin, X. Q. Li, X. Jin, X. Shen, X.... | https://arxiv.org/abs/2505.17654v1 |
Zhang, X. Chen, X. Nie, X. Sun, X. Wang, X. Cheng, X. Liu, X. Xie, X. Liu, X. Yu, X. Song, X. Shan, X. Zhou, X. Yang, X. Li, X. Su, X. Lin, Y . K. Li, Y . Q. Wang, Y . X. Wei, Y . X. Zhu, Y . Zhang, Y . Xu, Y . Xu, Y . Huang, Y . Li, Y . Zhao, Y . Sun, Y . Li, Y . Wang, Y . Yu, Y . Zheng, Y . Zhang, Y . Shi, Y . Xiong,... | https://arxiv.org/abs/2505.17654v1 |
Wang, J. Yu, J. Bitton, J. Spisak, J. Park, J. Rocca, J. Johnstun, J. Saxe, J. Jia, K. V . Alwala, K. Prasad, K. Upasani, K. Plawiak, K. Li, K. Heafield, K. Stone, K. El-Arini, K. Iyer, K. Malik, K. Chiu, K. Bhalla, K. Lakhotia, L. Rantala- Yeary, L. van der Maaten, L. Chen, L. Tan, L. Jenkins, L. Martin, L. Madaan, L.... | https://arxiv.org/abs/2505.17654v1 |
G. M. Florez, G. Schwarz, G. Badeer, G. Swee, G. Halpern, G. Herman, G. Sizov, Guangyi, Zhang, G. Lakshminarayanan, H. Inan, H. Shojanazeri, H. Zou, H. Wang, H. Zha, H. Habeeb, H. Rudolph, H. Suk, H. Aspegren, H. Goldman, H. Zhan, I. Damlaj, I. Molybog, I. Tufanov, I. Leontiadis, I.-E. Veliche, I. Gat, J. Weissman, J. ... | https://arxiv.org/abs/2505.17654v1 |
Garraghan. Bypassing prompt injection and jailbreak detection in llm guardrails, 2025. URL https://arxiv.org/abs/2504.11168 . [16] L. Huang, W. Yu, W. Ma, W. Zhong, Z. Feng, H. Wang, Q. Chen, W. Peng, X. Feng, B. Qin, and T. Liu. A survey on hallucination in large language models: Principles, taxonomy, challenges, and ... | https://arxiv.org/abs/2505.17654v1 |
Paino, A. Renzin, A. T. Passos, A. Kirillov, A. Christakis, A. Conneau, A. Kamali, A. Jabri, A. Moyer, A. Tam, A. Crookes, A. Tootoochian, A. Tootoonchian, A. Kumar, A. Vallone, A. Karpathy, A. Braunstein, A. Cann, A. Codispoti, A. Galu, A. Kondrich, A. Tulloch, A. Mishchenko, 13 A. Baek, A. Jiang, A. Pelisse, A. Woodf... | https://arxiv.org/abs/2505.17654v1 |
M. Janner, M. Lampe, M. Petrov, M. Wu, M. Wang, M. Fradin, M. Pokrass, M. Castro, M. O. T. de Castro, M. Pavlov, M. Brundage, M. Wang, M. Khan, M. Murati, M. Bavarian, M. Lin, M. Yesildal, N. Soto, N. Gimelshein, N. Cone, N. Staudacher, N. Summers, N. LaFontaine, N. Chowdhury, N. Ryder, N. Stathas, N. Turley, N. Tezak,... | https://arxiv.org/abs/2505.17654v1 |
J. Heidecke, C. Hesse, A. Hickey, W. Hickey, P. Hoeschele, B. Houghton, K. Hsu, S. Hu, X. Hu, J. Huizinga, S. Jain, S. Jain, J. Jang, A. Jiang, R. Jiang, H. Jin, D. Jin, S. Jomoto, B. Jonn, H. Jun, T. Kaftan, Łukasz Kaiser, A. Kamali, I. Kanitscheider, N. S. Keskar, T. Khan, L. Kilpatrick, J. W. Kim, C. Kim, Y . Kim, J... | https://arxiv.org/abs/2505.17654v1 |
Y . Fan, Y . Su, Y . Zhang, Y . Wan, Y . Liu, Z. Cui, Z. Zhang, and Z. Qiu. Qwen2.5 technical report, 2025. URL https://arxiv.org/abs/2412.15115 . [35] A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark, G. Krueger, and I. Sutskever. Learning transferable visual... | https://arxiv.org/abs/2505.17654v1 |
X. Wang, Y . Cao, Y . Liu, X. Wei, H. Zhang, H. Wang, W. Xu, H. Li, J. Wang, N. Deng, S. Li, Y . He, T. Jiang, J. Luo, Y . Wang, C. He, B. Shi, X. Zhang, W. Shao, J. He, Y . Xiong, W. Qu, P. Sun, P. Jiao, H. Lv, L. Wu, K. Zhang, H. Deng, J. Ge, K. Chen, L. Wang, M. Dou, L. Lu, X. Zhu, T. Lu, D. Lin, Y . Qiao, J. Dai, a... | https://arxiv.org/abs/2505.17654v1 |
classification criteria—play a crucial role in aligning model predictions with human judgment. Future research should explore structured, rule- aware prompting strategies that incorporate regulatory ontologies or logical trees to further enhance reasoning fidelity. Another key insight from our analysis is that many err... | https://arxiv.org/abs/2505.17654v1 |
17 Table 8: The prompt of Height Growth and Weight Loss products in Single violation. Data Type Chinese Prompt Height Growth#任务描述 请你根据给定信息和关键词，仔细判断对应的管控类型。给出最终的选项（一个到多个不等）。都不 相关返回Z.其他。 #管控类型 A.增高功效直接描述：明确使用以下词汇描述长高发育：增高、长高、长个、蹭蹭长/涨、xx岁还能 长、（身高）用了高/吃了高/喝了高/贴了高、吃出/喝出/补出/贴出高个子、描述商品使用前和使用后 身高差距。注意：若涉及未成年人进行此类表达，则不管控，其中未成年人... | https://arxiv.org/abs/2505.17654v1 |
The values to the left of the slash indicate partial accuracy, while those to the right indicate full accuracy. Overall Body. Women. Height. Men. Weight. Health. Open-source Models Llama-3.1-8B 35.62 / 20.93 64.85 / 62.38 68.25 / 49.29 33.82 / 11.03 37.27 / 26.38 38.01 / 10.86 17.59 / 10.61 Llama-3.1-70B 38.55 / 26.23 ... | https://arxiv.org/abs/2505.17654v1 |
(i) GPT-4o on Single-Violation (j) Claude-3.7 on Single-Violation (k) Gemini-2.5-pro on Single- Violation (l) Qwen-VL-Max on Single- Violation Figure 4: All VLMs’ performance on the Single-Violation task.22 (a) Qwen-3-32B on Single- Violation (b) Qwen-3-32B-think on Single- Violation (c) Qwen-3-30B-A3B on Single- Viola... | https://arxiv.org/abs/2505.17654v1 |
arXiv:2505.17656v1 [cs.CL] 23 May 2025Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs Hexiang TanαβFei Sunα/envel⌢peSha LiuβDu SuαQi CaoαXin Chenγ Jingang WangγXunliang CaiγYuanzhuo WangαHuawei ShenαβXueqi Chengαβ αState Key Laboratory of AI Safety, Institute of Computing Technology, CAS βUniversity... | https://arxiv.org/abs/2505.17656v1 |
al., 2022; Tian et al.; Xiong et al.), supervised probe-based (Azaria and Mitchell, 2023; Beigi et al., 2024; Zhu et al., 2024), and consistency-based methods. We find that all methods suffer substantial performance drops on self-consistent errors, in contrast to their strong performance on inconsistent errors. Consist... | https://arxiv.org/abs/2505.17656v1 |
tings in prior work (Kuhn et al., 2023). Next, we test pairwise semantic equivalence within {rg i, rs i,1, . . . , rs i,15}with the NLI -based criterion of Kuhn et al. (2023), treating two responses as equivalent if they mutually entail each other. An errorrg iis labeled self-consistent when all stochas- tic samples an... | https://arxiv.org/abs/2505.17656v1 |
self- consistent errors, as such consistent responses intu- itively exhibit higher probabilities. Therefore, we begin by systematically evaluating the performance of existing methods on self-consistent errors. 3How Well Do We Detect Self-Consistent Errors? This section evaluates the performance of current error detecti... | https://arxiv.org/abs/2505.17656v1 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.