80 citations · 174 across the 31 of their papers we have counts for
12 papers · 1 filter
Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods
Michal Moshkovitz, Suraj Srinivas, Lesia Semenova +7
Despite the proliferation of Explainable AI (XAI) techniques -- from feature attributions to sparse autoencoders -- explanations rarely influence real-world workflows. In practice,…
Prior Knowledge Makes It Possible: From Sublinear Graph Algorithms to LLM Test-Time Methods
Avrim Blum, Daniel Hsu, Cyrus Rashtchian +1
Test-time augmentation, such as Retrieval-Augmented Generation (RAG) or tool use, critically depends on an interplay between a model's parametric knowledge and externally retrieved…
Latent Concept Disentanglement in Transformer-based Language Models
Guan Zhe Hong, Bhavya Vasudeva, Vatsal Sharan +3
When large language models (LLMs) use in-context learning (ICL) to solve a new task, they must infer latent concepts from demonstration examples. This raises the question of whethe…
A Implies B: Circuit Analysis in LLMs for Propositional Logical Reasoning
Guan Zhe Hong, Nishanth Dikkala, Enming Luo +3
Due to the size and complexity of modern large language models (LLMs), it has proven challenging to uncover the underlying mechanisms that models use to solve reasoning problems. F…
Substance or Style: What Does Your Image Embedding Know?
Cyrus Rashtchian, Charles Herrmann, Chun-Sung Ferng +5
Probes are small networks that predict properties of underlying data from embeddings, and they provide a targeted, effective way to illuminate the information contained in embeddin…
A Theoretical View on Sparsely Activated Networks
Cenk Baykal, Nishanth Dikkala, Rina Panigrahy +2
Deep and wide neural networks successfully fit very complex functions today, but dense models are starting to be prohibitively expensive for inference. To mitigate this, one promis…
Probing Predictions on OOD Images via Nearest Categories
Yao-Yuan Yang, Cyrus Rashtchian, Ruslan Salakhutdinov +1
We study out-of-distribution (OOD) prediction behavior of neural networks when they classify images from unseen classes or corrupted images. To probe the OOD behavior, we introduce…
Unsupervised Embedding of Hierarchical Structure in Euclidean Space
Jinyu Zhao, Yi Hao, Cyrus Rashtchian
Deep embedding methods have influenced many areas of unsupervised learning. However, the best methods for learning hierarchical structure use non-Euclidean representations, whereas…
ExKMC: Expanding Explainable -Means Clustering
Nave Frost, Michal Moshkovitz, Cyrus Rashtchian
Despite the popularity of explainable AI, there is limited work on effective methods for unsupervised learning. We study algorithms for -means clustering, focusing on a trade-of…
A Closer Look at Accuracy vs. Robustness
Yao-Yuan Yang, Cyrus Rashtchian, Hongyang Zhang +2
Current methods for training robust networks lead to a drop in test accuracy, which has led prior works to posit that a robustness-accuracy tradeoff may be inevitable in deep learn…
Explainable -Means and -Medians Clustering
Sanjoy Dasgupta, Nave Frost, Michal Moshkovitz +1
Clustering is a popular form of unsupervised learning for geometric data. Unfortunately, many clustering algorithms lead to cluster assignments that are hard to explain, partially…
Robustness for Non-Parametric Classification: A Generic Attack and Defense
Yao-Yuan Yang, Cyrus Rashtchian, Yizhen Wang +1
Adversarially robust machine learning has received much recent attention. However, prior attacks and defenses for non-parametric classifiers have been developed in an ad-hoc or cla…