Large language models have demonstrated impressive performance on natural language tasks, but their decision-making processes remain opaque. Existing explanation methods either suffer from limited faithfulness to the model's reasoning or produce explanations that are difficult for humans to understand. To address these challenges, we propose ProtoSurE, a novel prototype-based surrogate framework that provides faithful and understandable explanations for LLMs. ProtoSurE trains an interpretable-by-design surrogate model that aligns with the target LLM while utilizing sentence-level prototypes as understandable concepts. Extensive experiments show that ProtoSurE consistently outperforms state-of-the-art explanation methods across diverse LLMs and datasets. Importantly, ProtoSurE demonstrates strong data efficiency, requiring relatively few training examples to achieve good performance, making it practical for real-world applications.

While bias in large language models (LLMs) is well-studied, similar concerns in vision-language models (VLMs) have received comparatively less attention. Existing VLM bias studies often focus on portrait-style images and gender-occupation associations, overlooking broader and more complex social stereotypes and their implied harm. This work introduces VIGNETTE, a large-scale VQA benchmark with 30M+ images for evaluating bias in VLMs through a question-answering framework spanning four directions: factuality, perception, stereotyping, and decision making. Beyond narrowly-centered studies, we assess how VLMs interpret identities in contextualized settings, revealing how models make trait and capability assumptions and exhibit patterns of discrimination. Drawing from social psychology, we examine how VLMs connect visual identity cues to trait and role-based inferences, encoding social hierarchies, through biased selections. Our findings uncover subtle, multifaceted, and surprising stereotypical patterns, offering insights into how VLMs construct social meaning from inputs.

Large vision-language models (LVLMs) achieve impressive performance on multimodal tasks but often suffer from hallucination and confidently describe objects or attributes not present in the image. Current training-free interventions struggle to maintain accuracy in open-ended and long-form generation scenarios. We introduce the Confidence-Aware Attention Calibration (CAAC) framework to address this challenge by targeting two key biases: spatial perception bias, which distributes attention disproportionately across image tokens, and modality bias, which shifts focus from visual to textual inputs over time. CAAC employs a two-step approach: Visual-Token Calibration (VTC) to balance attention across visual tokens, and Adaptive Attention Re-Scaling (AAR) to reinforce visual grounding guided by the model’s confidence. This confidence-driven adjustment ensures consistent visual alignment during generation. Experiments on CHAIR, AMBER, and POPE benchmarks demonstrate that CAAC outperforms baselines, particularly in long-form generations, effectively reducing hallucination. Data and code are available at https://github.com/mehrdadfazli/CAAC/.

In this work, we propose ProtoLens, a novel prototype-based model that provides finegrained, sub-sentence level interpretability for text classification.ProtoLens uses a Prototypeaware Span Extraction module to identify relevant text spans associated with learned prototypes and a Prototype Alignment mechanism to ensure prototypes are semantically meaningful throughout training.By aligning the prototype embeddings with human-understandable examples, ProtoLens provides interpretable predictions while maintaining competitive accuracy.Extensive experiments demonstrate that ProtoLens outperforms both prototype-based and non-interpretable baselines on multiple text classification benchmarks.

The success of deep neural networks (DNN) in solving general machine vision problems has agitated a wave of its adoption in automated visual inspection solutions. Especially, DNN is able to learn by itself those relevant image features to reach a model that is robust to image quality variation, which promises very scalable solutions. The correlation between image acquisition hardware and image processing software, which is typical in traditional solutions, is alleviated. On this basis, we propose a novel visual inspection service architecture that is scalable, economic and reliable. The realization challenges of the visual inspection service are analyzed and the corresponding designs in model composition and model scheduling are presented. Special focus is placed on the runtime performance of inspection models and the efficient use of the computing resources of contemporary commodity servers.