1 citations · 1 across the 3 of their papers we have counts for
3 papers · 1 filter
Capability Provenance in Language Models: A Case Study in Social Reasoning
Glenn Matlin, Chandreyi Chakraborty, Saehee Eom +8
We use training-data attribution as an interpretable tool for capability discovery, mapping which regions of the pretraining corpus support social reasoning versus STEM reasoning i…
LaSEr-Edit: Localized Span-level Error Editing with Energy-based Localization
Hye Ryung Son, Saehee Eom, Mooho Song +1
As large language models (LLMs) are widely adopted in real-world applications, it has become critical to ensure LLMs satisfy safety constraints, such as non-toxicity and logical co…
Data-efficient End-to-end Information Extraction for Statistical Legal Analysis
Wonseok Hwang, Saehee Eom, Hanuhl Lee +2
Legal practitioners often face a vast amount of documents. Lawyers, for instance, search for appropriate precedents favorable to their clients, while the number of legal precedents…