Related papers: VLG-CBM: Training Concept Bottleneck Models with V…

Recently, interpretable machine learning has re-explored concept bottleneck models (CBM). An advantage of this model class is the user's ability to intervene on predicted concept values, affecting the downstream output. In this work, we…

The increasing complexity of AI models, especially in deep learning, has raised concerns about transparency and accountability, particularly in high-stakes applications like medical diagnostics, where opaque models can undermine trust.…

Deep vision models often rely on biases learned from spurious correlations in datasets. To identify these biases, methods that interpret high-level, human-understandable concepts are more effective than those relying primarily on low-level…

Automated ICD-10 coding from clinical discharge summaries requires models that are both accurate on long-tailed multi-label classification tasks and interpretable to clinicians. Concept Bottleneck Models (CBMs) offer a principled framework…

Hallucinations in Large Language Models (LLMs) -- generations that are plausible but factually unfaithful -- remain a critical barrier to high-stakes deployment. Current detection methods typically rely on computationally expensive external…

In-Context Learning (ICL) has emerged as an important new paradigm in natural language processing and large language model (LLM) applications. However, the theoretical understanding of the ICL mechanism remains limited. This paper aims to…

Recent advances in Multi-modal Large Language Models (MLLMs) have predominantly focused on enhancing visual perception to improve accuracy. However, a critical question remains unexplored: Do models know when they do not know? Through a…

Language models (LMs) and their extension, vision-language models (VLMs), have achieved remarkable performance across various tasks. However, they still struggle with complex reasoning tasks that require multimodal or multilingual…

In recent years, the black-box nature of deep learning models has limited their application in high-stakes domains such as medical diagnosis and finance, where interpretability is essential. To address this, we propose a novel approach…

We introduce VLM-Lens, a toolkit designed to enable systematic benchmarking, analysis, and interpretation of vision-language models (VLMs) by supporting the extraction of intermediate outputs from any layer during the forward pass of…

Despite strong average-case performance, deep learning models often exhibit systematic errors on specific population groups, known as error slices. Identifying these groups and the root causes of their failures is critical for model…

Vision-language models (VLMs) have made substantial progress across a wide range of visual question answering benchmarks, spanning visual reasoning, document understanding, and multimodal dialogue. These improvements are evident in a wide…

Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to LLMs form Vision Language Models (VLMs). However, recent research shows that the visual modality in VLMs is highly…

This paper presents a novel training method, Conditional Masked Language Modeling (CMLM), to effectively learn sentence representations on large scale unlabeled corpora. CMLM integrates sentence representation learning into MLM training by…

The task of identifying multimodal image-text representations has garnered increasing attention, particularly with models such as CLIP (Contrastive Language-Image Pretraining), which demonstrate exceptional performance in learning complex…

Deploying AI-powered systems requires trustworthy models supporting effective human interactions, going beyond raw prediction accuracy. Concept bottleneck models promote trustworthiness by conditioning classification tasks on an…

Vision-language modeling (VLM) aims to bridge the information gap between images and natural language. Under the new paradigm of first pre-training on massive image-text pairs and then fine-tuning on task-specific data, VLM in the remote…

Sparse autoencoders (SAEs) promise a unified approach for mechanistic interpretability, concept discovery, and model steering in LLMs and LVLMs. However, realizing this potential requires learned features to be both interpretable and…

Recent advancements have enhanced the capability of Multimodal Large Language Models (MLLMs) to comprehend multi-image information. However, existing benchmarks primarily evaluate answer correctness, overlooking whether models genuinely…

Explainable AI seeks to bring light to the decision-making processes of black-box models. Traditional saliency-based methods, while highlighting influential data segments, often lack semantic understanding. Recent advancements, such as…