Related papers: Evaluating Brain-Inspired Modular Training in Auto…

We introduce Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable. Inspired by brains, BIMT embeds neurons in a geometric space and augments the loss function with a cost proportional to…

Large language models (LLMs) have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque. Mechanistic interpretability (i.e., the systematic study of how neural networks…

While large transformer models excel in predictive performance, their lack of interpretability restricts their usefulness in high-stakes domains. To remedy this, we propose the Generalized Induction-Head Model (GIM), an interpretable model…

Large Language Models (LLMs) have shown impressive performance across a wide range of tasks. However, the size of LLMs is steadily increasing, hindering their application on computationally constrained environments. On the other hand,…

This review synthesizes the nascent but critical field of developmental interpretability for Large Language Models. We chart the field's evolution from static, post-hoc analysis of trained models to a dynamic investigation of the training…

Through considerable effort and intuition, several recent works have reverse-engineered nontrivial behaviors of transformer models. This paper systematizes the mechanistic interpretability process they followed. First, researchers choose a…

Large Language Models (LLMs) are widely deployed in real-world applications, yet their internal mechanisms remain difficult to interpret and control, limiting our ability to diagnose and correct undesirable behaviors. Mechanistic…

The upsurge in pre-trained large models started by ChatGPT has swept across the entire deep learning community. Such powerful models demonstrate advanced generative ability and multimodal understanding capability, which quickly set new…

Interpretable machine learning has exploded as an area of interest over the last decade, sparked by the rise of increasingly large datasets and deep neural networks. Simultaneously, large language models (LLMs) have demonstrated remarkable…

Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. We present a pipeline that bridges circuit-level…

This survey paper delves into the emerging and critical area of symbolic knowledge distillation in Large Language Models (LLMs). As LLMs like Generative Pre-trained Transformer-3 (GPT-3) and Bidirectional Encoder Representations from…

Large language models (LLMs) are often portrayed as merely imitating linguistic patterns without genuine understanding. We argue that recent findings in mechanistic interpretability (MI), the emerging field probing the inner workings of…

Mechanistic interpretability aims to understand the inner workings of large neural networks by identifying circuits, or minimal subgraphs within the model that implement algorithms responsible for performing specific tasks. These circuits…

Pre-trained large language models (LLM) are starting to be widely used in many applications. In this work, we explore the use of these models in interactive machine translation (IMT) environments. In particular, we have chosen mBART…

Mechanistic interpretability seeks to understand the neural mechanisms that enable specific behaviors in Large Language Models (LLMs) by leveraging causality-based methods. While these approaches have identified neural circuits that copy…

In the rapidly evolving landscape of artificial intelligence, multi-modal large language models are emerging as a significant area of interest. These models, which combine various forms of data input, are becoming increasingly popular.…

Large Language Models (LLMs) like GPT and LLaMA are revolutionizing the AI industry with their sophisticated capabilities. Training these models requires vast GPU clusters and significant computing time, posing major challenges in terms of…

As large language models (LLMs) continue to advance, there is a growing urgency to enhance the interpretability of their internal knowledge mechanisms. Consequently, many interpretation methods have emerged, aiming to unravel the knowledge…

This study is a pioneering endeavor to investigate the capabilities of Large Language Models (LLMs) in addressing conceptual questions within the domain of mechanical engineering with a focus on mechanics. Our examination involves a…

The vast number of parameters in large language models (LLMs) endows them with remarkable capabilities, allowing them to excel in a variety of natural language processing tasks. However, this complexity also presents challenges, making LLMs…