Related papers: Towards Vision-Language Mechanistic Interpretabili…

Human Multimodal Language Understanding (MLU) aims to infer human intentions by integrating related cues from heterogeneous modalities. Existing works predominantly follow a ``learning to attend" paradigm, which maximizes mutual information…

Recent advances in causal interpretability have extended from language models to vision-language models (VLMs), seeking to reveal their internal mechanisms through input interventions. While textual interventions often target semantics,…

Neural networks are widely regarded as black-box models, creating significant challenges in understanding their inner workings, especially in natural language processing (NLP) applications. To address this opacity, model explanation…

Multimodal Large Language Models (MLLMs) have showcased exceptional Chain-of-Thought (CoT) reasoning ability in complex textual inference tasks including causal reasoning. However, will these causalities remain straightforward when crucial…

Contrastive Language-Image Pre-training (CLIP) learns rich representations via readily available supervision of natural language. It improves the performance of downstream vision tasks, including but not limited to the zero-shot, long tail,…

Model interpretability is crucial for understanding and trusting the decisions made by complex machine learning models, such as those built with XGBoost. SHAP (SHapley Additive exPlanations) values have become a popular tool for…

Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…

Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of…

Recent advancements in Large Language Models (LLMs) have facilitated the development of Multimodal LLMs (MLLMs). Despite their impressive capabilities, MLLMs often suffer from over-reliance on unimodal biases (e.g., language bias and vision…

Writing is a universal cultural technology that reuses vision for symbolic communication. Humans display striking resilience: we readily recognize words even when characters are fragmented, fused, or partially occluded. This paper…

Modular vision-language models (Vision-LLMs) align pretrained image encoders with (frozen) large language models (LLMs) and post-hoc condition LLMs to `understand' the image input. With the abundance of readily available high-quality…

Vision-Language models (VLMs) achieve strong performance on multimodal tasks but often fail at systematic visual reasoning tasks, leading to inconsistent or illogical outputs. Neuro-symbolic methods promise to address this by inducing…

Vision-Language Models (VLMs) have advanced multi-modal tasks like image captioning, visual question answering, and reasoning. However, they often generate hallucinated outputs inconsistent with the visual context or prompt, limiting…

In this paper, we introduce a novel interpreting framework that learns an interpretable model based on an ontology-based sampling technique to explain agnostic prediction models. Different from existing approaches, our algorithm considers…

Building explainable systems is a critical problem in the field of Natural Language Processing (NLP), since most machine learning models provide no explanations for the predictions. Existing approaches for explainable machine learning…

This paper presents several novel findings on the explainability of vision reflection in large multimodal models (LMMs). First, we show that prompting an LMM to verify the prediction of a specialized vision model can improve recognition…

Automated interpretability research aims to identify concepts encoded in neural network features to enhance human understanding of model behavior. Within the context of large language models (LLMs) for natural language processing (NLP),…

Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of reasoning, planning, and acting within interactive environments. Despite their growing capability to perform multi-step reasoning and decision-making…

Interpretable machine learning tackles the important problem that humans cannot understand the behaviors of complex machine learning models and how these models arrive at a particular decision. Although many approaches have been proposed, a…

Mechanistic interpretability seeks to uncover how internal components of neural networks give rise to predictions. A persistent challenge, however, is disentangling two often conflated notions: decodability--the recoverability of…