Related papers: Concept Bottleneck Large Language Models

Large language models (LLMs) are the result of a massive experiment in bottom-up, data-driven reverse engineering of language at scale. Despite their utility in a number of downstream NLP tasks, ample research has shown that LLMs are…

Large language models (LLMs) are increasingly used to meet user information needs, but their effectiveness in dealing with user queries that contain various types of ambiguity remains unknown, ultimately risking user trust and satisfaction.…

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…

The rapid evolution of machine learning (ML) has led to the widespread adoption of complex "black box" models, such as deep neural networks and ensemble methods. These models exhibit exceptional predictive performance, making them…

Concept Bottleneck Models (CBMs) tackle the opacity of neural architectures by constructing and explaining their predictions using a set of high-level concepts. A special property of these models is that they permit concept interventions,…

Since the advent of ChatGPT, Large Language Models (LLMs) have excelled in various tasks but remain as black-box systems. Understanding the reasoning bottlenecks of LLMs has become a critical challenge, as these limitations are deeply tied…

Neural network models of language have long been used as a tool for developing hypotheses about conceptual representation in the mind and brain. For many years, such use involved extracting vector-space representations of words and using…

Recently impressive performance has been achieved in Concept Bottleneck Models (CBM) by utilizing the image-text alignment learned by a large pre-trained vision-language model (i.e. CLIP). However, there exist two key limitations in concept…

A lively ongoing debate is taking place, since the extraordinary emergence of Large Language Models (LLMs) with regards to their capability to understand the world and capture the meaning of the dialogues in which they are involved.…

Large Language Models (LLMs) have achieved unprecedented breakthroughs in various natural language processing domains. However, the enigmatic ``black-box'' nature of LLMs remains a significant challenge for interpretability, hampering…

Multi-modal large language models (MLLMs) have shown incredible capabilities in a variety of 2D vision and language tasks. We extend MLLMs' perceptual capabilities to ground and reason about images in 3-dimensional space. To that end, we…

The increasing use of neural networks in various applications has lead to increasing apprehensions, underscoring the necessity to understand their operations beyond mere final predictions. As a solution to enhance model transparency,…

Semantic text embedding is essential to many tasks in Natural Language Processing (NLP). While black-box models are capable of generating high-quality embeddings, their lack of interpretability limits their use in tasks that demand…

Transforming a large language model (LLM) into a Vision-Language Model (VLM) can be achieved by mapping the visual tokens from a vision encoder into the embedding space of an LLM. Intriguingly, this mapping can be as simple as a shallow MLP…

Large Language Models(LLMs) have revolutionized text generation and multimodal perception,but their capabilities in 3D content generation remain underexplored. Existing methods compromise by producing either low-resolution meshes or coarse…

Today's deep learning systems deliver high performance based on end-to-end training. While they deliver strong performance, these systems are hard to interpret. To address this issue, we propose Semantic Bottleneck Networks (SBN): deep…

Large language models (LLMs) have substantially advanced machine learning research, including natural language processing, computer vision, data mining, etc., yet they still exhibit critical limitations in explainability, reliability,…

LLMs have revolutionized the field of artificial intelligence and have emerged as the de-facto tool for many tasks. The current established technology of LLMs is to process input and generate output at the token level. This is in sharp…

Humans organize knowledge into compact conceptual categories that balance compression with semantic richness. Large Language Models (LLMs) exhibit impressive linguistic abilities, but whether they navigate this same compression-meaning…

A central goal of cognitive modeling is to develop models that not only predict human behavior but also provide insight into the underlying cognitive mechanisms. While neural network models trained on large-scale behavioral data often…