4 papers
ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior
Florian Eichin, Yupei Du, Philipp Mondorf +3
Post-hoc interpretability methods typically attribute a model's behavior to its components, data, or training trajectory in isolation, and are often tied to a particular level of g…
Language models can learn implicit multi-hop reasoning, but only if they have lots of training data
Yuekun Yao, Yupei Du, Dawei Zhu +2
Implicit reasoning is the ability of a language model to solve multi-hop reasoning tasks in a single forward pass, without chain of thought. We investigate this capability using GP…
Reason to Rote: Rethinking Memorization in Reasoning
Yupei Du, Philipp Mondorf, Silvia Casola +3
Large language models readily memorize arbitrary training instances, such as label noise, yet they perform strikingly well on reasoning tasks. In this work, we investigate how lang…
On Support Samples of Next Word Prediction
Yuqian Li, Yupei Du, Yufang Liu +3
Language models excel in various tasks by making complex decisions, yet understanding the rationale behind these decisions remains a challenge. This paper investigates \emph{data-c…