Papers by Juho Lee
Mind the Blind Spots: A Focus-Level Evaluation Framework for LLM Reviews (2025.emnlp-main)
Copied to clipboard
Hyungyu Shin, Jingyu Tang, Yoonjoo Lee, Nayoung Kim, Hyunseung Lim, Ji Yong Cho, Hwajung Hong, Moontae Lee, Juho Kim
| Challenge: | Large Language Models (LLMs) can automatically draft reviews, but determining whether they are trustworthy requires systematic evaluation. |
| Approach: | They propose an automatic focus-level evaluation pipeline based on two sets of facets . authors evaluated LLM reviews at surface-level or content-level . |
| Outcome: | The proposed framework enables automatic evaluation of paper reviews based on two sets of facets . the framework compared open review paper reviews with human experts on validity, clarity, novelty . |
Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing datasets for hate speech detection neglect the cultural diversity within a single language. |
| Approach: | They propose a CR**oss-cultural **E**nglish **Hate* speech dataset that uses culturally hateful keywords to identify posts from four countries plus the United States. |
| Outcome: | The proposed dataset shows that only 56.2% of the posts in CREHate achieve consensus among all countries, with the highest pairwise label difference rate of 26%. |
SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models (2025.findings-acl)
Copied to clipboard
Seanie Lee, Dong Bok Lee, Dominik Wagner, Minki Kang, Haebin Seong, Tobias Bocklet, Juho Lee, Sung Ju Hwang
| Challenge: | Deploying large language models (LLMs) requires robust safety guard models to detect and block harmful user prompts. |
| Approach: | They propose a binary router that selectively applies a larger safety guard model to the data that the router considers hard. |
| Outcome: | The proposed method outperforms baselines on multiple benchmark datasets on hard and hard examples. |
Learning to Perturb Word Embeddings for Out-of-distribution QA (2021.acl-long)
Copied to clipboard
| Challenge: | QA models that are pretraining with unlabeled data can overfit and may not generalize well to unseen data that falls outside the training distribution. |
| Approach: | They propose a method which perturbs word embedding without changing their semantics. |
| Outcome: | The proposed method outperforms baseline methods on five target domains on a single source dataset on five different target domain domains. |
Learning with Limited Data for Multilingual Reading Comprehension (D19-1)
Copied to clipboard
| Challenge: | Existing approaches to support question answering in a new language with limited training resources introduce noises to the training data due to translation or generation errors. |
| Approach: | They propose a weakly-supervised framework that quantifies noises from automatically generated labels to deemphasize or fix noisy data in training. |
| Outcome: | The proposed framework can deemphasize or fix noisy data in training on low-resource languages with varying similarity to English. |
ArxivDIGESTables: Synthesizing Scientific Literature into Tables using Language Models (2024.emnlp-main)
Copied to clipboard
Benjamin Newman, Yoonjoo Lee, Aakanksha Naik, Pao Siangliulue, Raymond Fok, Juho Kim, Daniel Weld, Joseph Chee Chang, Kyle Lo
| Challenge: | Using language models (LMs) can generate literature review tables by decomposing it into separate schema and value generation steps. |
| Approach: | They propose a framework that leverages language models to perform literature review table generation by decomposing it into separate schema and value generation steps. |
| Outcome: | The proposed framework decomposes the task into two sub-tasks: schema generation and value generation. |