18 citations · 49 across the 20 of their papers we have counts for
20 papers
Data-Efficient Adaptation of LLMs via Attention Head Reweighting
Tuomas Oikarinen, Zixiao Chen, Charlotte Siska +3
Learning effectively from limited data is critical in domains like security where labeled examples are scarce. Large language models (LLMs) have demonstrated some capabilities for…
Multimodal Concept Bottleneck Models
Tongqing Shi, Ge Yan, Tuomas Oikarinen +1
Concept Bottleneck Models (CBMs) enhance the interpretability of deep learning networks by aligning the features extracted from images with natural concepts. However, existing CBMs…
CI-CBM: Class-Incremental Concept Bottleneck Model for Interpretable Continual Learning
Amirhosein Javadi, Tuomas Oikarinen, Tara Javidi +1
Catastrophic forgetting remains a fundamental challenge in continual learning, in which models often forget previous knowledge when fine-tuned on a new task. This issue is especial…
Faithful and Stable Neuron Explanations for Trustworthy Mechanistic Interpretability
Ge Yan, Tuomas Oikarinen, Tsui-Wei +1
Neuron identification is a popular tool in mechanistic interpretability, aiming to uncover the human-interpretable concepts represented by individual neurons in deep networks. Whil…
Evaluating Neuron Explanations: A Unified Framework with Sanity Checks
Tuomas Oikarinen, Ge Yan, Tsui-Wei Weng
Understanding the function of individual units in a neural network is an important building block for mechanistic interpretability. This is often done by generating a simple text e…
Beyond Top Activations: Efficient and Reliable Crowdsourced Evaluation of Automated Interpretability
Tuomas Oikarinen, Ge Yan, Akshay Kulkarni +1
Interpreting individual neurons or directions in activation space is an important topic in mechanistic interpretability. Numerous automated interpretability methods have been propo…
Interpretable Generative Models through Post-hoc Concept Bottlenecks
Akshay Kulkarni, Ge Yan, Chung-En Sun +2
Concept bottleneck models (CBM) aim to produce inherently interpretable models that rely on human-understandable concepts for their predictions. However, existing approaches to des…
Concept Bottleneck Language Models For protein design
Aya Abdelsalam Ismail, Tuomas Oikarinen, Amy Wang +8
We introduce Concept Bottleneck Protein Language Models (CB-pLM), a generative masked language model with a layer where each neuron corresponds to an interpretable concept. Our arc…
Concept Bottleneck Large Language Models
Chung-En Sun, Tuomas Oikarinen, Berk Ustun +1
We introduce Concept Bottleneck Large Language Models (CB-LLMs), a novel framework for building inherently interpretable Large Language Models (LLMs). In contrast to traditional bl…
Crafting Large Language Models for Enhanced Interpretability
Chung-En Sun, Tuomas Oikarinen, Tsui-Wei Weng
We introduce the Concept Bottleneck Large Language Model (CB-LLM), a pioneering approach to creating inherently interpretable Large Language Models (LLMs). Unlike traditional black…
Linear Explanations for Individual Neurons
Tuomas Oikarinen, Tsui-Wei Weng
In recent years many methods have been developed to understand the internal workings of neural networks, often by describing the function of individual neurons in the model. Howeve…
Interpreting Neurons in Deep Vision Networks with Language Models
Nicholas Bai, Rahul A. Iyer, Tuomas Oikarinen +2
In this paper, we propose Describe-and-Dissect (DnD), a novel method to describe the roles of hidden neurons in vision networks. DnD utilizes recent advancements in multimodal deep…
Corrupting Neuron Explanations of Deep Visual Features
Divyansh Srivastava, Tuomas Oikarinen, Tsui-Wei Weng
The inability of DNNs to explain their black-box behavior has led to a recent surge of explainability methods. However, there are growing concerns that these explainability methods…
The Importance of Prompt Tuning for Automated Neuron Explanations
Justin Lee, Tuomas Oikarinen, Arjun Chatha +3
Recent advances have greatly increased the capabilities of large language models (LLMs), but our understanding of the models and their safety has not progressed as fast. In this pa…
Concept-Monitor: Understanding DNN training through individual neurons
Mohammad Ali Khan, Tuomas Oikarinen, Tsui-Wei Weng
In this work, we propose a general framework called Concept-Monitor to help demystify the black-box DNN training processes automatically using a novel unified embedding space and c…
Label-Free Concept Bottleneck Models
Tuomas Oikarinen, Subhro Das, Lam M. Nguyen +1
Concept bottleneck models (CBM) are a popular way of creating more interpretable neural networks by having hidden layer neurons correspond to human-understandable concepts. However…
CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
Tuomas Oikarinen, Tsui-Wei Weng
In this paper, we propose CLIP-Dissect, a new technique to automatically describe the function of individual hidden neurons inside vision networks. CLIP-Dissect leverages recent ad…
GraphMDN: Leveraging graph structure and deep learning to solve inverse problems
Tuomas P. Oikarinen, Daniel C. Hannah, Sohrob Kazerounian
The recent introduction of Graph Neural Networks (GNNs) and their growing popularity in the past few years has enabled the application of deep learning algorithms to non-Euclidean,…
Robust Deep Reinforcement Learning through Adversarial Loss
Tuomas Oikarinen, Wang Zhang, Alexandre Megretski +2
Recent studies have shown that deep reinforcement learning agents are vulnerable to small adversarial perturbations on the agent's inputs, which raises concerns about deploying suc…
Landslide Geohazard Assessment With Convolutional Neural Networks Using Sentinel-2 Imagery Data
Silvia L. Ullo, Maximillian S. Langenkamp, Tuomas P. Oikarinen +4
In this paper, the authors aim to combine the latest state of the art models in image recognition with the best publicly available satellite images to create a system for landslide…