3 papers
cs.IR2024
eXplainable Bayesian Multi-Perspective Generative Retrieval
EuiYul Song, Philhoon Oh, Sangryul Kim +1
Modern deterministic retrieval pipelines prioritize achieving state-of-the-art performance but often lack interpretability in decision-making. These models face challenges in asses…
cs.CL2023
Detrimental Contexts in Open-Domain Question Answering
Philhoon Oh, James Thorne
For knowledge intensive NLP tasks, it has been widely accepted that accessing more information is a contributing factor to improvements in the model's end-to-end performance. Howev…
cs.CL2023
Knowledge Corpus Error in Question Answering
Yejoon Lee, Philhoon Oh, James Thorne
Recent works in open-domain question answering (QA) have explored generating context passages from large language models (LLMs), replacing the traditional retrieval step in the QA…