相关论文: NeuronScope: A Multi-Agent Framework for Explainin…

Leveraging Multi-modal Large Language Models (MLLMs) to accelerate frontier scientific research is promising, yet how to rigorously evaluate such systems remains unclear. Existing benchmarks mainly focus on single-document understanding,…

Neurons are the fundamental building blocks of deep neural networks, and their interconnections allow AI to achieve unprecedented results. Motivated by the goal of understanding how neurons encode information, compositional explanations…

Neural networks often contain polysemantic neurons that respond to multiple, sometimes unrelated, features, complicating mechanistic interpretability. We introduce the Polysemanticity Index (PSI), a null-calibrated metric that quantifies…

A variety of methods have been proposed for interpreting nodes in deep neural networks, which typically involve scoring nodes at lower layers with respect to their effects on the output of higher-layer nodes (where lower and higher layers…

Large language models (LLMs) have recently demonstrated remarkable capabilities to comprehend human intentions, engage in reasoning, and design planning-like behavior. To further unleash the power of LLMs to accomplish complex tasks, there…

Neuroscience data are highly fragmented across labs, formats, and experimental paradigms, and reuse often requires substantial manual effort. A persistent roadblock to data reuse and integration is the need to decipher bespoke and diverse…

We present neuron embeddings, a representation that can be used to tackle polysemanticity by identifying the distinct semantic behaviours in a neuron's characteristic dataset examples, making downstream manual or automatic interpretation…

Lexical semantic change has primarily been investigated with observational and experimental methods; however, observational methods (corpus analysis, distributional semantic modeling) cannot get at causal mechanisms, and experimental…

Interpreting individual neurons in deep neural networks is a crucial step towards understanding their complex decision-making processes and ensuring AI safety. Despite recent progress in neuron labeling, existing methods often limit the…

Scene graphs have emerged as a structured and serializable environment representation for grounded spatial reasoning with Large Language Models (LLMs). In this work, we propose SG^2, an iterative Schema-Guided Scene-Graph reasoning…

Neural NLP models are increasingly accurate but are imperfect and opaque---they break in counterintuitive ways and leave end users puzzled at their behavior. Model interpretation methods ameliorate this opacity by providing explanations for…

Large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, yet their internal mechanisms remain largely opaque. In this paper, we introduce a simple, lightweight, and broadly applicable method with a focus on…

We are interested in image manipulation via natural language text -- a task that is useful for multiple AI applications but requires complex reasoning over multi-modal spaces. We extend recently proposed Neuro Symbolic Concept Learning…

While large language models (LLMs) have demonstrated strong capability in structured prediction tasks such as semantic parsing, few amounts of research have explored the underlying mechanisms of their success. Our work studies different…

LLMs are increasingly used to support qualitative research, yet existing systems produce outputs that vary widely--from trace-faithful summaries to theory-mediated explanations and system models. To make these differences explicit, we…

The era of Large Language Models (LLMs) presents a new opportunity for interpretability--agentic interpretability: a multi-turn conversation with an LLM wherein the LLM proactively assists human understanding by developing and leveraging a…

In the study of neural network interpretability, there is growing evidence to suggest that relevant features are encoded across many neurons in a distributed fashion. Making sense of these distributed representations without knowledge of…

Deciphering the human visual experience through brain activities captured by fMRI represents a compelling and cutting-edge challenge in the field of neuroscience research. Compared to merely predicting the viewed image itself, decoding…

Learning to solve long horizon temporally extended tasks with reinforcement learning has been a challenge for several years now. We believe that it is important to leverage both the hierarchical structure of complex tasks and to use expert…

In recent years, there has been increasing attention on the capabilities of large models, particularly in handling complex tasks that small-scale models are unable to perform. Notably, large language models (LLMs) have demonstrated…