Yanai Elazar

Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals

2020 · arXiv (Cornell University)

A growing body of work makes use of probing to investigate the working of neural models, often considered black boxes. Recently, an ongoing debate emerged surrounding the limitations of the probing paradigm. In this work, …

OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens

2025 · arXiv (Cornell University)

We present OLMoTrace, the first system that traces the outputs of language models back to their full, multi-trillion-token training data in real time. OLMoTrace finds and shows verbatim matches between segments of language model output …

oLMpics-On What Language Model Pre-training Captures

2020 · Transactions of the Association for Computational Linguistics

Recent success of pre-trained language models (LMs) has spurred widespread interest in the language capabilities that they possess. However, efforts to understand whether LM representations are useful for symbolic reasoning tasks have been limited and …

Measuring and Improving Consistency in Pretrained Language Models

2021 · Transactions of the Association for Computational Linguistics

Abstract Consistency of a model—that is, the invariance of its behavior under meaning-preserving alternations in its input—is a highly desirable property in natural language processing. In this paper we study the question: Are Pretrained Language …