60 citations · 68 across the 12 of their papers we have counts for
13 papers
Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models
Ruixuan Deng, Xiaoyang Hu, Miles Gilberti +5
We identify semantically coherent, context-consistent network components in large language models (LLMs) using coactivation of sparse autoencoder (SAE) features collected from just…
Transparent and Coherent Procedural Mistake Detection
Shane Storks, Itamar Bar-Yossef, Yayuan Li +3
Procedural mistake detection (PMD) is a challenging problem of classifying whether a human user (observed through egocentric video) has successfully executed a task (specified by a…
Can Foundation Models Watch, Talk and Guide You Step by Step to Make a Cake?
Yuwei Bao, Keunwoo Peter Yu, Yichi Zhang +6
Despite tremendous advances in AI, it remains a significant challenge to develop interactive task guidance systems that can offer situated, personalized guidance and assist humans…
From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning
Zheyuan Zhang, Shane Storks, Fengyuan Hu +4
Pre-trained language models (PLMs) have shown impressive performance in various language tasks. However, they are prone to spurious correlations, and often generate illusory inform…
In-Context Analogical Reasoning with Pre-Trained Language Models
Xiaoyang Hu, Shane Storks, Richard L. Lewis +1
Analogical reasoning is a fundamental capacity of human cognition that allows us to reason abstractly about novel situations by relating them to past experiences. While it is thoug…
NLP Reproducibility For All: Understanding Experiences of Beginners
Shane Storks, Keunwoo Peter Yu, Ziqiao Ma +1
As natural language processing (NLP) has recently seen an unprecedented level of excitement, and more people are eager to enter the field, it is unclear whether current research re…