Hide and Seek (HnS) is a concept‑level attribution method that interprets black‑box vision models without needing model weights or labeled concept datasets. It retrieves concept‑aligned images via a vision‑language model, localizes and masks the concept region, and measures attribution by observing changes in the model’s output. HnS was validated on CelebA and COCO‑Stuff, showing stronger agreement with ground‑truth attributions than existing methods, and was applied to tasks like image captioning and satellite image segmentation where other concept attribution methods fail.
By Bhanu Tokas, Rahul Nair, Rockwell Jackson, Hannah Kerner
The paper introduces Ra‑NEM, a method that optimizes the area under insertion and deletion curves to improve the faithfulness of feature importance attributions in machine learning models. By deriving an objective function from faithfulness and approximating its gradient, the authors link insertion curves to top‑k feature selection, enabling a loss function that measures attribution quality. Ra‑NEM, integrated with the neural explanation mask framework, works with any differentiable model, yielding accurate, robust, and fast attributions that outperform existing algorithms on multiple XAI metrics.
By Bj{\o}rn Leth M{\o}ller, Bulat Ibragimov, Christian Igel
arXiv:2602.07008v5 Announce Type: replace
Abstract: Reliable models should not only predict correctly, but also base their decisions on acceptable evidence. However, conventional supervised learning...
By Ruoyu Chen, Shangquan Sun, Xiaoqing Guo, Kangwei Liu, Sanyi Zhang, Zhangcheng Wang, Shiming Liu, Qunli Zhang, Wei Wang, Hua Zhang, Xiaochun Cao
arXiv:2606. 08497v1 Announce Type: new Abstract: As deep language models (DLMs) are increasingly deployed in high-stakes domains such as healthcare, understanding their decision rationale becomes paramount for ensuring trust, safety, and accountability.
By Minyoung Hwang, Seokhyun Lee, Changhee Lee
arXiv:2607. 12052v1 Announce Type: cross Abstract: Synthetic image attribution aims at identifying the generator responsible for a given AI-generated image.
By Meiling Li, Pietro Bongini, Benedetta Tondi, Mauro Barni
Matryoshka Attribution (MAttr) is a mask‑learning method that identifies nested subsets of a language model’s internal components by minimizing downstream loss. It uses a differentiable sigmoid top‑k operator and randomizes sparsity during training to produce an attribution ordering of components. MAttr tops the Mechanistic Interpretability Benchmark leaderboard and can be applied via reinforcement learning to pinpoint weight changes that control behaviors such as refusal in Llama 3.1 8B Instruct, where restoring just 1% of weights removes refusals while preserving capabilities.
By Aryaman Arora, Kirill Acharya, Nathan Hu, Yanzhe Zhang, Noah Goodman, Dan Jurafsky, Christopher Potts
arXiv:2610.17898v1 Announce Type: cross
Abstract: Sparse autoencoders decompose language model representations into interpretable features, but feature interpretation in this literature remains predo...
By Samuel Xie, Noura Al-Moubayed
arXiv:2601. 22276v2 Announce Type: replace Abstract: As Text-to-Image (T2I) diffusion models are increasingly used in real-world creative workflows, a principled framework for valuing contributors who provide a collection of data is essential for fair compensation and sustainable data marketplaces.
By Mingyu Lu, Soham Gadgil, Chris Lin, Chanwoo Kim, Su-In Lee
CiteVQA is a benchmark that evaluates multimodal large language models on both answering document questions and providing element‑level bounding‑box citations for the evidence used. It contains 1,897 questions across 711 PDFs in seven domains and two languages, with ground‑truth citations generated via an automated pipeline and strict quality control. The evaluation metric, Strict Attributed Accuracy (SAA), rewards a prediction only when both the answer and the cited region are correct, revealing widespread attribution hallucination in current models.
By Dongsheng Ma, Jiayu Li, Zhengren Wang, Yijie Wang, Jiahao Kong, Weijun Zeng, Jutao Xiao, Jie Yang, Bangrui Xu, Yuhan Wang, Bin Wang, Conghui He
arXiv:2602. 07008v3 Announce Type: replace-cross Abstract: Reliable models should not only predict correctly, but also justify decisions with acceptable evidence.
By Ruoyu Chen, Shangquan Sun, Xiaoqing Guo, Sanyi Zhang, Kangwei Liu, Shiming Liu, Zhangcheng Wang, Qunli Zhang, Wei Wang, Hua Zhang, Xiaochun Cao
arXiv:2606. 07690v1 Announce Type: cross Abstract: Finetuning data selection requires balancing two competing goals: selecting examples that improve the downstream objective, and doing so without repeatedly finetuning models.
By Ning Wang, Zhengxin Zhang, Maosen Tang, Yitang Gao, Claire Cardie, Sainyam Galhotra
arXiv:2610.17827v1 Announce Type: new
Abstract: Existing approaches to training and evaluating search agents focus heavily on final-answer quality, largely neglecting how generated answers map back t...
By Haochen Zhao, Minsheng Hao, Zheng Li, Yifan Li, Zikang Liu, Bowen Qin, Yuhao Cheng, Chuang Fan, Haosheng Zou, Jeff Chen, Sujian Li