Papers by Keonwoong Noh
Exploring the Impact of Corpus Diversity on Financial Pretrained Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing financial PLMs are not pretrained on sufficiently diverse financial data, leading to subpar generalization performance. |
| Approach: | They propose to pretrain financial PLMs on financial corpus and train financial models on financial data. |
| Outcome: | The proposed financial language models outperform existing financial PLMs on financial tasks even for unseen corpus groups. |
Automatic Transmission for LLM Tiers: Optimizing Cost and Accuracy in Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are powerful tools for a wide range of natural language tasks. |
| Approach: | They propose an LLM automatic transmission framework that automatically selects LLM tiers without training. |
| Outcome: | The proposed framework achieves superior performance while reducing costs. |
Beyond Reference: Evaluating High Quality Translations Better than Human References (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing machine translation metrics give maximum score to reference sentence . however, these metrics overlook the possibility that candidate sentences outperform reference sentences in terms of quality. |
| Approach: | They propose a machine translation metrics that give an absolute score to a translated sentence based on the similarity with the reference sentence. |
| Outcome: | The proposed measure outperforms existing MT metrics in terms of quality and assigns positive scores to candidates that outperformed reference sentences. |