text string | source string |
|---|---|
19747 294983 5.85×10−4 Yelp2018 31668 38048 1561406 1.30×10−3 Movielens-1M 6940 3706 1000209 3.89×10−2 4.1.2 Prediction Metrics. Following the standard evaluation pro- tocols commonly used for the CF tasks [ 28,36], We employ a full- rank evaluation approach where we rank all uninteracted items alongside the positive i... | https://arxiv.org/abs/2505.22649v1 |
it incorporates a more sophisticated attention aggregation method with more parameters. •Retrain . When unlearning requests are received, a full retraining of the entire graph model is carried out with model parameters being re-initialized. This can be regraded as ground truth. 4.1.7 Implementation Settings. We develop... | https://arxiv.org/abs/2505.22649v1 |
UnlearnRec shows strong unlearning results. Across datasets and backbones, UnlearnRec achieves MI-BF and MI-NG values above 1. MI-BF > 1 shows reduced probability of recom- mending edges marked for unlearning versus before. Similarly, MI-NG > 1 means unlearned edges are less likely to be recom- mended than negative sam... | https://arxiv.org/abs/2505.22649v1 |
0.2486 0.2394 0.2398 0.2540 0.2477 NDCG 0.1584 0.1703 0.1618 0.1432 0.1453 0.1486 0.1399 0.1453 0.1429 0.1505 0.1618 0.1558 0.1508 0.1599 0.1524 0.1545 0.1670 0.1611 MI-BF 7.6745 15.4290 8.7485 1.4975 1.2150 1.7941 1.5865 1.0238 1.8937 1.1470 1.0322 1.1283 1.0030 1.0432 1.0076 5.3729 4.3520 2.6285 MI-NG 3.9265 7.7154 4... | https://arxiv.org/abs/2505.22649v1 |
be recommended like other normal positive instances. •-𝐹𝑖𝑛𝑒𝑇𝑢𝑛𝑒 : In our experiment of adversarial attacks, we found that even without fine-tuning the pre-trained influence encoder(IE), we could still achieve good results (both in utility and ef- ficacy) when unlearning requests were received and directly appli... | https://arxiv.org/abs/2505.22649v1 |
ScoreProbabilityGCN, After Retraining (a) Prediction distribution of GCN after unlearning on Movielens-1M dataset 4 2 0 2 4 6 810 Link Prediction ScoreProbabilityGIF, SGL, After Unlearning 6 4 2 0246810 Link Prediction ScoreProbabilityGraphEraser, SGL, After Unlearning 6 4 2 02468 Link Prediction ScoreProbabilityOurs, ... | https://arxiv.org/abs/2505.22649v1 |
three datasets. Dataset Retrain GraphEraser GIF CEU Ours(0) Ours(1) Ours(2) Ours(3) ML-1M 1208.354 993.064 8.278 6.943 0.312 7.034 14.221 21.517 Yelp2018 3029.606 1834.413 146.384 52.216 0.468 19.71 39.201 56.023 Gowalla 839.07 795.995 131.753 39.089 0.432 3.37 6.734 10.026 •High Memory Cost for IF-based Methods . IF m... | https://arxiv.org/abs/2505.22649v1 |
unlearning cases in Fig. 6. It can be observed that when a particular interaction is unlearned, its prediction score is significantly reduced (comparable to that of a negative interaction edge), and the prediction scores of items similar to it also decrease slightly. However, the scores for these similar items remain s... | https://arxiv.org/abs/2505.22649v1 |
introduce UnlearnRec: a novel pretraining para- digm for recommendation unlearning that is both model-agnostic and learnable. Our approach effectively addresses the complex chal- lenges of unlearning in modern recommender systems, particularly excelling in advanced SSL-based architectures where traditional methods fall... | https://arxiv.org/abs/2505.22649v1 |
[15] Zachary Izzo, Mary Anne Smart, Kamalika Chaudhuri, and James Zou. 2021. Approximate data deletion from machine learning models. In International Con- ference on Artificial Intelligence and Statistics (AISTATS) . PMLR, 2008–2016. [16] Chanhee Kwak, Junyeong Lee, Kyuhong Park, and Heeseok Lee. 2017. Let machines unl... | https://arxiv.org/abs/2505.22649v1 |
Transactions on Neural Networks and Learning Systems (TNNLS) 32, 1 (2020), 4–24. [34] Lianghao Xia, Chao Huang, Chunzhen Huang, Kangyi Lin, Tao Yu, and Ben Kao. 2023. Automated Self-Supervised Learning for Recommendation. In The ACM Web Conference (WWW) . 992–1002. [35] Junliang Yu, Hongzhi Yin, Xin Xia, Tong Chen, Liz... | https://arxiv.org/abs/2505.22649v1 |
arXiv:2505.22655v1 [cs.LG] 28 May 2025Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents Michael Kirchhof1Gjergji Kasneci2Enkelejda Kasneci2 Abstract Large-language models (LLMs) and chatbot agents are known to provide wrong outputs at times, and it was recently found that this can ... | https://arxiv.org/abs/2505.22655v1 |
with more data from new regions of the input mani- fold to produce more definite outputs. Aleatoric uncertainty is irreducible uncertainty, when the data itself is too noisy or lacks features to make predictions that come without a risk of error, regardless of how good the model is. While these uncertainty quantificati... | https://arxiv.org/abs/2505.22655v1 |
infor- mation can help resolve the uncertainty. This is better suited to the dynamic multi-turn nature of chat interactions where, as we show below, what initially appears as epistemic uncer- tainty (e.g., lack of knowledge) can become aleatoric uncer- tainty if additional information fails to reduce the ambiguity, and... | https://arxiv.org/abs/2505.22655v1 |
reliable predictions, but definitions vary dra- matically. This definition conflict that can be seen directly in a simple example. Suppose a learner is parametrized by θ and models a binary classification problem. In this section, we focus on only one input sample x∈ X, so the learner is simply tasked to estimate the p... | https://arxiv.org/abs/2505.22655v1 |
has neither a maximal nor minimal uncertainty, since the density values depend on the normal- ization and prior over the whole space X(or, analogously, X × Y ). Hence, in the above example, latent density esti- mators would answer neither with maximum nor minimum uncertainty but rather ’it depends’, namely on how much ... | https://arxiv.org/abs/2505.22655v1 |
al., 2024; and similarly Aposto- lakis, 1990; Helton, 1997). This is also a corollary of ax- iomatic views that dictate that ”in the limit, i.e., if the sam- ple size goes to infinity, all epistemic uncertainty should dis- appear” (Bengs et al., 2022) so that model bias could not be part of the epistemic uncertainty an... | https://arxiv.org/abs/2505.22655v1 |
et al., 2018; Mukhoti et al., 2023; Wimmer et al., 2023), Bregman decomposi- tions (Pfau, 2013; Gupta et al., 2022; Gruber et al., 2023), or logit decompositions (Kendall & Gal, 2017). But does this clean division hold in practice? For example, Depeweg et al. (2018) define HP(y|x)(y)|{z} predictive=EQ(θ|x) HP(y|θ,x)(y... | https://arxiv.org/abs/2505.22655v1 |
the latter arguments on epistemic approxi- mation uncertainty about the aleatoric uncertainty estimator (H¨ullermeier et al., 2022; Valdenegro-Toro & Mori, 2022) also hold in more generality. To account for these dependen- cies between aleatoric and epistemic uncertainty estimators, recent methods (Mukhoti et al., 2023... | https://arxiv.org/abs/2505.22655v1 |
tainty” (Der Kiureghian & Ditlevsen, 2009). Der Kiureghian & Ditlevsen (2009) conclude that calling an uncertainty aleatoric or epistemic is ultimately a subjective choice made by the modeler that just serves to communicate 3We change the example of Der Kiureghian & Ditlevsen (2009) from tabular data to chatbots, becau... | https://arxiv.org/abs/2505.22655v1 |
nor epistemic. Still, we need to dis- tinguish the task-underspecification uncertainty from other uncertainties in the next-token distribution P(y|x), for ex- 6 Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents ample those that arise from lack of knowledge or from se- mantic equiva... | https://arxiv.org/abs/2505.22655v1 |
chooses follow-up questions to be able to provide a better answer to the current user interaction. There are two key characteristics that distinguish interactive learning from active learning: First, the learning is only in order to better solve the current problem x, rather than learning about other inputs to improve ... | https://arxiv.org/abs/2505.22655v1 |
one-answer interactions. 3.3. Output Uncertainties Once the LLM agent has determined its underspecification uncertainties, and possibly reduced some of it via interac- tive learning, it is tasked to communicate all leftover uncer- tainty in its answer. In its most popular traditional form, this would be a probability s... | https://arxiv.org/abs/2505.22655v1 |
This is mostly a question of fine- tuning the LLM, but also a question on aligning the meaning of those words to what humans interpret them as, necessi- tating human-computer interaction research (Van Der Bles et al., 2019; Belem et al., 2024; Steyvers et al., 2024; Bel ´em et al., 2024). When the LLM agent does not co... | https://arxiv.org/abs/2505.22655v1 |
in a form. Since these interactions are standardized, there should be plenty of training data similar to or even equal to the current context, so that the LLM agent knows which follow-up questions to ask just by reciting past interactions. There would be no need for researching interactive learning. In this specific sc... | https://arxiv.org/abs/2505.22655v1 |
B´alint Mucs ´anyi. The exchanges on what the true nature of aleatoric and epistemic uncertainty is, if there is any at all, have motivated and shaped this work. Impact Statement This paper presents work whose goal is to advance the field of Machine Learning. We have highlighted potential ben- efits in transparency and... | https://arxiv.org/abs/2505.22655v1 |
models to emit linguistic expressions of uncertainty, 2024. Ivo Pascal de Jong, Andreea Ioana Sburlea, and Matias Valdenegro-Toro. How disentangled are your classifi- cation uncertainties? arXiv preprint arXiv:2408.12175 , 2024. Stefan Depeweg, Jose-Miguel Hernandez-Lobato, Finale Doshi-Velez, and Steffen Udluft. Decom... | https://arxiv.org/abs/2505.22655v1 |
Gordon Wilson. Large language models must be taught to know what they don’t know. arXiv preprint arXiv:2406.08391 , 2024.Enkelejda Kasneci, Kathrin Seßler, Stefan K ¨uchemann, Maria Bannert, Daryna Dementieva, Frank Fischer, Urs Gasser, Georg Groh, Stephan G ¨unnemann, Eyke H¨ullermeier, et al. Chatgpt for good? on opp... | https://arxiv.org/abs/2505.22655v1 |
awareness. Advances in Neural Information Processing Systems (NeurIPS) , 2020. Sewon Min, Julian Michael, Hannaneh Hajishirzi, and Luke Zettlemoyer. AmbigQA: Answering ambiguous open- domain questions. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) , 2020. B´alint Mucs... | https://arxiv.org/abs/2505.22655v1 |
faithfully express their intrinsic uncertainty in words? In Yaser Al-Onaizan, Mohit Bansal, and Yun- Nung Chen (eds.), Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , 2024. Dongkeun Yoon, Seungone Kim, Sohee Yang, Sunkyoung Kim, Soyeon Kim, Yongil Kim, Eunbi Choi, Yireun Kim, an... | https://arxiv.org/abs/2505.22655v1 |
3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model Wenbo Hu1BYining Hong1Yanjun Wang1Leison Gao1Zibu Wei1 Xingcheng Yao1Nanyun Peng1Yonatan Bitton2Idan Szpektor2Kai-Wei Chang1 1University of California, Los Angeles,2Google Research https://3dllm-mem.github.io Prepare a most suitable prese... | https://arxiv.org/abs/2505.22657v1 |
and episodic memory, and purposeful action planning — cognitive processes that humans take for granted — remain formidable challenges for embodied AI systems today. Recent extensions of Large Language Models (LLMs) to 3D environments have birthed 3D- LLMs (Hong et al., 2023b; Guo et al., 2023; Gu et al., 2024; Huang et... | https://arxiv.org/abs/2505.22657v1 |
introduce 3DLLM-M EM, a 3D embodied LLM with dynamic memory management capabilities designed specifically for embodied spatial-temporal reasoning, planning and acting. To our knowledge, we are among the first to explore dense 3D representations as memory for embodied 3D LLMs — addressing a significant gap in current re... | https://arxiv.org/abs/2505.22657v1 |
Memory Benchmark 2.1 Overview of 3DM EM-BENCH Design principles Long-term memory (Camina and Güell, 2017; Friedman et al., 2018; Zlotnik and Vansintjan, 2019) can be categorized into explicit memory andimplicit memory . Explicit memory includes semantic memory , which stores general knowledge and facts about the world,... | https://arxiv.org/abs/2505.22657v1 |
previous exploration and the difference that matters for your current observation. A: The previous rooms contained storage cabinets, beds, dressers, and kitchen counters …… This room uniquely features a wardrobe extending along an entire wall and does not contain any pictures, lamps ……. In-domain Tasks In-the-wild Task... | https://arxiv.org/abs/2505.22657v1 |
3: (a) We propose 3DLLM-M EM, a memory-enhanced 3D embodied agent that gradually form its long-term memory while executing tasks. Multiple timesteps are shown together but in different colors, with each timestep’s memory including the prior one. The task is “prepare a simple breakfast” as shown in Figure 2. (b) Overvie... | https://arxiv.org/abs/2505.22657v1 |
into LLM space asXp∈RV×d×w×h, where h=H P , w=W P , anddrepresents LLM’s hidden dimension. The 3D positions in the 3D world are obtained with known depth image, camera intrinsic and extrinsic parameters and are further encoded into 3D position embeddings P∈RV×d×w×h. These are directly added to the 2D patch visual t... | https://arxiv.org/abs/2505.22657v1 |
is updated accordingly. Thus, the memory bank remains dynamic and reflects the latest state of the explored environments. As described in §2.2, environment changes and corresponding observations are pre-collected and stored locally to facilitate efficient data loading during both training and inference. 4 Experiments I... | https://arxiv.org/abs/2505.22657v1 |
is conducted on 8 Google Cloud TPU v5p cores with a batch size of 256. Our model is trained using supervised fine-tuning (SFT) with a standard language modeling loss. More details are provided in Appendix D. Baselines We compare 3DLLM-M EMagainst a broad range of memory management approaches: •Everything in Context. Fo... | https://arxiv.org/abs/2505.22657v1 |
require long-term spatial-temporal reasoning. 3D-Mem demonstrates improved performance in EQA over other baseline approaches. However, it falls short on spatial relation, navigation and object counting tasks, indicating the limitation of relying solely on aggregated image- centric memories. 3DLLM-M EMsignificantly outp... | https://arxiv.org/abs/2505.22657v1 |
the development of embodied AI agents. Grounded in these environments, some existing benchmarks focus on high-level planning tasks, typically involving short trajectories that can often be completed within single-room settings, thereby requiring minimal spatial-temporal memory (Shridhar et al., 2020, 2021; Li et al., 2... | https://arxiv.org/abs/2505.22657v1 |
3DLLM-M EMdoes not involve low-level navigation and control policy, but utilizes high-level pre- 9 defined policies in simulator for carrying out the actions. We think that such aspects are orthogonal to our study, and could be explored and seamlessly integrated into our framework in the future. References Kevin Black,... | https://arxiv.org/abs/2505.22657v1 |
Weihs, Oscar Michel, Eli VanderBilt, Ludwig Schmidt, Kiana Ehsani, Aniruddha Kembhavi, and Ali Farhadi. 2023. Objaverse: A universe of annotated 3d objects. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023 , pages 13142–13153. IEEE. 4 Xingjian Diao, C... | https://arxiv.org/abs/2505.22657v1 |
LeBlanc, Sergey Levine, Adrian Li-Bell, Mohith Mothukuri, Suraj Nair, Karl Pertsch, Allen Z. Ren, Lucy Xiaoyang Shi, Laura Smith, Jost Tobias Springenberg, Kyle Stachowicz, James Tanner, Quan Vuong, Homer Walke, Anna Walling, Haohuan Wang, Lili Yu, and Ury Zhilinsky. 2025. π0.5: a vision-language-action model with open... | https://arxiv.org/abs/2505.22657v1 |
Galuba, Andrew Westbury, Angel X Chang, Manolis Savva, Yili Zhao, and Dhruv Batra. 2021. Habitat-matterport 3d dataset (HM3d): 1000 large-scale 3d environments for embodied AI. volume abs/2109.08238. 4, 9 Bokui Shen, Fei Xia, Chengshu Li, Roberto Martín-Martín, Linxi Fan, Guanzhi Wang, Claudia Pérez-D’Arpino, Shyamal B... | https://arxiv.org/abs/2505.22657v1 |
Batra. 2019. Embodied question answering in photorealistic environments with point cloud perception. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019 , pages 6659–6668. Computer Vision Foundation / IEEE. 9 Quanting Xie, So Yeon Min, Pengliang Ji, Yue Yang, ... | https://arxiv.org/abs/2505.22657v1 |
The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024 . OpenReview.net. 8 Chenming Zhu, Tai Wang, Wenwei Zhang, Jiangmiao Pang, and Xihui Liu. 2024. Llava-3d: A simple yet effective pathway to empowering lmms with 3d-awareness. ArXiv preprint , abs/2409.18125. 2, 5... | https://arxiv.org/abs/2505.22657v1 |
are discarded because no reliable vertical evidence is present. Horizontal limits are simply the minimum and maximum coordinates of the room’s floor and ceiling points, and together these six coordinates constitute the room’s axis -aligned bounding box. Based on the bounding boxes for each room, we calculate the boundi... | https://arxiv.org/abs/2505.22657v1 |
I can pick up box(0).", "<PUT DOWN flower vase(0) from room(8) on desk(0) in room(10)>", "Now I will pick up box(0) from cabinet(0).", "<PICK UP box(0) from room(10) in room(10)>", "Now I will put box(0) on the desk(0) so I can pick up printer(0).", "<PUT DOWN box(0) from room(10) on desk(0) in room(10)>", "Now I will ... | https://arxiv.org/abs/2505.22657v1 |
DOWN tomatoes(0) from room(8) on countertop(1) in room(8)>", "<PICK UP eggs(0) from room(8) in room(8)>", 16 "<PUT DOWN eggs(0) from room(8) on countertop(1) in room(8)>", "<PICK UP cooking pan(0) from room(8) in room(8)>", "<PUT DOWN cooking pan(0) from room(8) on stove(0) in room(8)>", "I remember I saw apron in room... | https://arxiv.org/abs/2505.22657v1 |
For pick-up and put-down validation, the agent is allowed to hold only one object at a time. A command is considered invalid if the agent attempts to pick up an object while already holding one, or tries to put down an object when its hand is empty. Finally, after all commands have been executed, if the trajectory ends... | https://arxiv.org/abs/2505.22657v1 |
but couldn’t find it after exploration of rooms. It has to change to a another similar object to complete its task. Inventory and Action Constraints: The agent can only hold one item at a time. Never perform consecutive PICK UP or PUT DOWN actions. If the agent holds an item, it must put it down before picking up anoth... | https://arxiv.org/abs/2505.22657v1 |
are scene, room and object semantics along with their bounding boxes. {Input agent’s trajectory} is the 3D agent’s explored trajectories and action chains. G Evaluation Setup Details 3D-LLM Similar to the 3D-LLM work (Hong et al., 2023b), we use their direct reconstruction method to extract the 3D features from each sc... | https://arxiv.org/abs/2505.22657v1 |
summarization of common things and differences. For clarity, consider these examples: {In-context examples} ——————- Here is the scene information: {Input scene information} Here is current room you are in and previous rooms you went: {Input agent’s location} Table 6: Prompt template for generate QA data. {In-context ex... | https://arxiv.org/abs/2505.22657v1 |
and lounging zones. Bed(0) extends along one side, with pillow (0) near its head and cabinet (1) beside it, which supports decoration (0) and is flanked by book (0) and book (1). Near the foot of bed(0), yoga mat (0), bag(0), and box(0) form a small activity area. At the far end, wardrobe (0) stands near wall(4), next ... | https://arxiv.org/abs/2505.22657v1 |
arXiv:2505.22660v1 [cs.LG] 28 May 2025Maximizing Confidence Alone Improves Reasoning Mihir Prabhudesai∗ Carnegie Mellon UniversityLili Chen* Carnegie Mellon UniversityAlex Ippolitin* Carnegie Mellon University Katerina Fragkiadaki Carnegie Mellon UniversityHao Liu Carnegie Mellon UniversityDeepak Pathak Carnegie Mellon... | https://arxiv.org/abs/2505.22660v1 |
distributions. This signal is dense, general, and easy to compute, requiring no ground-truth answers. Importantly, not all parts of the response contribute equally to final performance. Through empirical analysis, we find that minimizing entropy over tokens near the end of the reasoning chain, especially those correspo... | https://arxiv.org/abs/2505.22660v1 |
where a model is updated using data from the test distribution, without access to ground-truth labels. The goal is to improve performance in scenarios where there is a distribution shift between training and testing environments. Methods for adapting without labels include normalization techniques that recalibrate feat... | https://arxiv.org/abs/2505.22660v1 |
under the current policy π, while the second term computes the average reward across the reference group. The learning signal is thus the improvement in reward relative to these baselines. For more details, we refer the reader to Shao et al. [37]. 3.3 Entropy Reward For a given prompt x, the model generates a response ... | https://arxiv.org/abs/2505.22660v1 |
comprised of 83 problems from the 2022 and 2023 AMC12 exams, which are given to 12th grade students. Although the original problems are in multiple-choice format, the dataset presents modified versions of the problem which expect an integer solution. •AIME24 [ 23]: The American Invitational Mathematics Examination (AIM... | https://arxiv.org/abs/2505.22660v1 |
points simply because they do not know how to put their answers in the right format. For example, GSM8K expects answers after " #### " and MATH500 expects final answers to be placed in "boxed". A nontrivial amount of engineering effort has gone into both designing prompts that encourage correct formatting and implement... | https://arxiv.org/abs/2505.22660v1 |
TTRL. GSM8K MATH500 AMC AIME GPQA Qwen2.5-7B-Instruct w/ TTRL 0.929 0.822 0.521 0.172 0.361 w/ RENT (Ours) 0.900 0.823 0.501 0.270 0.368 TTRL [ 57] is a concurrent work to ours which uses majority voting as a reward. Figure 2 shows the performance of RENT and TTRL with Qwen2.5-7B-Instruct on GSM8K, MATh500, AMC, AIME, ... | https://arxiv.org/abs/2505.22660v1 |
and accuracy for each of these strategies on three datasets. While most token selection strategies do result in a positive correlation between confidence and accuracy, we note that the "last chunk" strategy has a significantly higher correlation compared to the "first chunk" strategy. This suggests that the most import... | https://arxiv.org/abs/2505.22660v1 |
regimes where external supervision is unavailable. 9 References [1]David Berthelot, Nicholas Carlini, Ian Goodfellow, Nicolas Papernot, Avital Oliver, and Colin A Raffel. Mixmatch: A holistic approach to semi-supervised learning. Advances in neural information processing systems , 32, 2019. [2]Maciej Besta, Nils Blach,... | https://arxiv.org/abs/2505.22660v1 |
7969–7992, 2023. [18] Saurav Kadavath, Tom Conerly, Amanda Askell, Tom Henighan, Dawn Drain, Ethan Perez, Nicholas Schiefer, Zac Hatfield-Dodds, Nova DasSarma, Eli Tran-Johnson, et al. Language models (mostly) know what they know. arXiv preprint arXiv:2207.05221 , 2022. [19] Adam Tauman Kalai and Santosh S Vempala. Cal... | https://arxiv.org/abs/2505.22660v1 |
Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel R Bowman. Gpqa: A graduate-level google-proof q&a benchmark. In First Conference on Language Modeling , 2024. [34] Kuniaki Saito, Donghyun Kim, Stan Sclaroff, Trevor Darrell, and Kate Saenko. Semi-supervised domain adaptation via minimax entropy. In Proceedings of... | https://arxiv.org/abs/2505.22660v1 |
Huang, Zhen Li, Suhang Wang, and Qi He. A survey of calibration process for black-box llms. arXiv preprint arXiv:2412.12767 , 2024. [50] Miao Xiong, Zhiyuan Hu, Xinyang Lu, Yifei Li, Jie Fu, Junxian He, and Bryan Hooi. Can llms express their uncertainty? an empirical evaluation of confidence elicitation in llms. arXiv ... | https://arxiv.org/abs/2505.22660v1 |
arXiv:2505.15516v1 [cs.LG] 21 May 2025Journal of Machine Learning Research 1 (2025) 1-33 Submitted 4/00; Published 10/00 Explainable embeddings with Distance Explainer Christiaan Meijer c.meijer@esciencecenter.nl E. G. Patrick Bos p.bos@esciencecenter.nl Netherlands eScience Center Science Park 402 (Matrix THREE) 1098 ... | https://arxiv.org/abs/2505.15516v1 |
2024). A variety of XAI methods have been developed to interpret and explain model predictions, and these can be broadly categorized based on their approach. Much of the work done for embedded spaces specifically has been focused on the interpretability1 of the spaces or the model as a whole (Boselli et al., 2024). Met... | https://arxiv.org/abs/2505.15516v1 |
the model different parts that potentially hold the most meaning when they’re combined, as opposed to masking isolated regions and ignoring the meaning of combinations of parts. This way, it is sensitive to a wide range of semantic contents. Task The RISE implementation accompanying the original paper (Petsiuk et al., ... | https://arxiv.org/abs/2505.15516v1 |
image is low, the masked pixels apparently did not contain much salient information. Hence, masks associated with them should contribute to (through the sum over masks) highlighting minimally salient regions. In contrast, masks associated with high distances contribute to highlighting maximally salient regions2. Select... | https://arxiv.org/abs/2505.15516v1 |
input item to the next were very small, typically below 10−4. Weights based on these distances are very close together and hence do not distinguish the importance of one mask from another in a numerically significant way in the RISE algorithm. RISE was designed for weights in the range of [0 ,1]. Our first attempt to s... | https://arxiv.org/abs/2505.15516v1 |
corresponding vector element gives the activation of the model on that class. While this would not typically be considered an embedded space vector, it is structurally similar and can be interpreted as a kind of semantic vector in an albeit quite arbitrary but in fact also quite well defined space. This latter fact mak... | https://arxiv.org/abs/2505.15516v1 |
salient enough for CLIP? 6. To do this in other data domains one needs to define a good masking function for that modality. In the DIANNA project (Ranguelova et al., 2024), we have implemented masking for text, tables and time-series (Meijer, 2024). 7 Meijer and Bos Labradoodle image - “a labradoodle” Single salient ob... | https://arxiv.org/abs/2505.15516v1 |
see the respective “model scores” of these orders, in our case simply the resulting distance. LoDF and HiDF orders are shown in blue in separate panels, while random order is shown in both images in orange. LoDF distance: 0.79% distance: 1.63% distance: 1.39% distance: 1.47% distance: 1.35% HiDF distance: -69.80% dista... | https://arxiv.org/abs/2505.15516v1 |
fly, with high confidence. There is almost nothing to gain here, and therefore any change in distance is small, comparable to random pixel removal. The second experiment compares two bee images. Two results in particular caught our attention: 1. Why is the striped part of the bee (the posterior segment) not highlighted... | https://arxiv.org/abs/2505.15516v1 |
still scores highest in the bee dimensions. In other words, it still looks like a bee. This can be confirmed by looking at the last column in figure 3. The same happens in the HiDF order. Only the last 5% changes the model’s activations. Changes occur after removing more of the image than in the random order. 4.2 Sensi... | https://arxiv.org/abs/2505.15516v1 |
modes: incrementally shuffling layers top-down, incre- mentally bottom-up and shuffling each layer independently. After perturbing the layers, MPRT summarizes its assessment in a metric: the Spearman correlation between the origi- nal “unperturbed” attribution map (i.e. without random perturbation of model layers) and ... | https://arxiv.org/abs/2505.15516v1 |
0.61 9 -0.11 0.02 0.32 10 -0.15 0.03 0.60 11 -0.13 -0.03 0.56 12 -0.19 0.02 0.63 13 -0.19 0.01 0.41 14 -0.21 -0.03 0.42 15 -0.27 -0.01 0.54 16 -0.22 0.02 0.18 Table 1: MPRT scores 4.3.1 How to interpret these results? Consider these two hypothetical extremes: 1. The attribution map almost remains unchanged as a result ... | https://arxiv.org/abs/2505.15516v1 |
As well as thus providing our opinionated guide on how to interpret the attribution maps, this will cover aspects of performance that are overly complex to quantify. For instance, we will show that Nauta’s Consistency (Nauta et al., 2023) can be achieved in section 5.2.1. Contrastivity is tested by assessing the output... | https://arxiv.org/abs/2505.15516v1 |
first impression is that these attributions seem slightly less sharp in their delineations of the salient areas of interest. This might be an artifact of the model or of the fact that the pa- rameters used in both cases may be less ideal for this model than for the image-versus-image cases. Nevertheless, the performanc... | https://arxiv.org/abs/2505.15516v1 |
comparing the bee image to the fly image. 22 Explainable embeddings with Distance Explainer As noted before, the numbers in table 2 do not generalize to all use-cases of Distance Explainer. Different resolution images, particular embedding models, etcetera, will require fine-tuning of the number of masks. Also changing... | https://arxiv.org/abs/2505.15516v1 |
also increases the relative amplitude of possibly already lingering noisy patches, thus increasing the appearance of noise. This is illustrated in figure 11a. The second case is that of an image of a car compared to the caption “a bicycle”, as shown in figure 11b. In this case, we found that there are two interesting p... | https://arxiv.org/abs/2505.15516v1 |
as for the image-versus- image case. This matches our earlier observation of figure 9 in section 5.1. 24 Explainable embeddings with Distance Explainer feature resolution: 2 4 6 8 12 16 24 32 64 1280.50 0.25 0.000.250.50 0.4 0.2 0.00.20.4 0.4 0.2 0.00.20.4 0.4 0.2 0.00.20.4 0.4 0.2 0.00.20.4 0.2 0.00.2 0.2 0.00.2 0.2 0... | https://arxiv.org/abs/2505.15516v1 |
comparison). From left to right, the percentage of selected masks is increased. 26 Explainable embeddings with Distance Explainer 5.3.2 Threshold value Having chosen the two-sided “mirror” approach, we next studied the effect in this mode on the selection range of distance rank-ordered masks. Figure 15 shows how an inc... | https://arxiv.org/abs/2505.15516v1 |
the appropriate number of masks and filtering criteria. The method’s reliance on random masking introduces a trade-off between computational cost and stability of results. Addi- tionally, we expect that different embedding models may require tailored distance metrics to better capture the underlying structure of their ... | https://arxiv.org/abs/2505.15516v1 |
authors. References Reduan Achtibat, Maximilian Dreyer, Ilona Eisenbraun, Sebastian Bosse, Thomas Wie- gand, Wojciech Samek, and Sebastian Lapuschkin. From attribution maps to human- understandable explanations through concept relevance propagation. Nature Machine Intelligence , 5(9):1006–1019, 9 2023. ISSN 2522-5839. ... | https://arxiv.org/abs/2505.15516v1 |
Distance Explainer Gelly, Jakob Uszkoreit, and Neil Houlsby. An image is worth 16x16 words: Transformers for image recognition at scale, 2021. URL https://arxiv.org/abs/2010.11929 . Krishna Gade, Sahin Cem Geyik, Krishnaram Kenthapadi, Varun Mithal, and Ankur Taly. Explainable ai in industry. In Proceedings of the 25th... | https://arxiv.org/abs/2505.15516v1 |
Agar- wal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. Learning transferable visual models from natural language supervision, 2021. URL https://arxiv.org/abs/2103.00020 . Elena Ranguelova, Patrick Bos, Yang Liu, Christiaan Meijer, Fakhereh (Sarah) Alidoost, Leon Oostr... | https://arxiv.org/abs/2505.15516v1 |
arXiv:2505.15517v1 [cs.RO] 21 May 2025Robo2VLM: Visual Question Answering from Large-Scale In-the-Wild Robot Manipulation Datasets Kaiyuan Chen1,∗Shuangyu Xie1,∗Zehan Ma1Ken Goldberg1 1University of California, Berkeley∗Equal contribution {kych, syxie, zehanma, goldberg}@berkeley.edu https://huggingface.co/datasets/kep... | https://arxiv.org/abs/2505.15517v1 |
Modalities: stereo (depth) imagesScene UnderstandingKey Modalities: gripper state, Side+Wrist ViewRobot State - GripperKey Modalities: 2 Side View, Wrist ViewTask State - Success Q: In the left image (ext1 camera), a red dot is marked. Which point is the closest point in the right image (ext2 camera) corresponding to t... | https://arxiv.org/abs/2505.15517v1 |
VLMs, robotics datasets from Open -X-Embodiment contains rich sensory-modal including RGB video, proprioceptive [31,28,32,33,34,35,36,37,38,39,40,41,42,43,44], depth data [ 31,28,32,33,35], and force-torque [ 37,39,40,41], that reflect the dynamics of interaction. These information presents an opportunity to bridge rob... | https://arxiv.org/abs/2505.15517v1 |
core manipulation skills such as spatial relationship, goal conditions, and interaction understanding. Robo2VLM instantiates 3 Left CamRight Cam Wrist CamRobo2VLM Scene-interaction Understanding Keyframe selectionSemantic SegmentationManipulation Phase Classification Embodied Question Template QueryObject info, current... | https://arxiv.org/abs/2505.15517v1 |
D t Spatial Relationship What’s the relative direction in 3 -D between end effector and {target object} ?IRGB t,pEE t Scene Understanding Which point is closer to the camera viewing the scene? IRGB t, IStereo t Multiple View Which point in the right -side image corresponds to the point in the left-side image?IStereo t ... | https://arxiv.org/abs/2505.15517v1 |
a large angular separation in the projected 2D image. To detect guessing by hallucination, we randomly replace some correct answers with "None of Above" option. 5 OverallTotal samples: 60,000QuestionsAvg. length: 108.69 chMedian length: 113.00 chMin length: 28 chMax length: 378 chChoicesAvg. # / Q: 4.65Avg. length: 14.... | https://arxiv.org/abs/2505.15517v1 |
To address this, we select a compact set of keyframes that retain essential semantic and visual cues while reducing redundancy and data volume. These keyframes are extracted from the multi-modal robot trajectory T={Ot}T t=1based on manipulation phase transition, scene coverage diversity and context visibility. 4 Robo2V... | https://arxiv.org/abs/2505.15517v1 |
49 .77 Qwen 2.5 VL-7B 30.63 41 .68 55 .63 21 .55 24 .38 17 .32 33 .01 42 .57 7 .82 25 .71 46 .61 39 .73 Qwen 2.5 VL-32B 37.68 49.39 71.37 21 .8528.53 17.5034.21 55.08 12.90 30 .45 63 .80 49 .32 Qwen 2.5 VL-72B 37.76 38.8485.00 22.31 28.23 15 .71 28 .47 51 .89 10 .08 33.96 71.09 54.79 CoT Reasoning LLaV A 1.5-7B 21.61 2... | https://arxiv.org/abs/2505.15517v1 |
to the final answer." We run a simultaneous Llama-3.2-3B-Instruct to extract model outputs for final letter answer. We focus fine-tuning on language layers (both attention and MLP modules) while keeping vision layers frozen. For each configuration, we use random 2000 questions from the testing set. For consistency, all... | https://arxiv.org/abs/2505.15517v1 |
in Figure 4, increasing the fine-tuning data generally leads to notable performance enhancements across most VQA categories. Significant gains are observed in ‘Object State’ understanding, where accuracy improved from 29.34% to 80.24%. “Task State-success” also sees a substantial rise from 47.65% to 68.03%. Other categ... | https://arxiv.org/abs/2505.15517v1 |
understanding, while there is a significant gap to human in reasoning fine-grained spatial relationship and interactions. Evaluation also suggests that finetuning Robo2VLM-1 dataset improves in spatial and interaction reasoning. Future work will focus on generalizing Robo2VLM to a wider range of robot embodiments and g... | https://arxiv.org/abs/2505.15517v1 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.