Papers by Hyunwoo Lee
SLM as Guardian: Pioneering AI Safety with Small Language Model (2024.emnlp-industry)
Copied to clipboard
Ohjoon Kwon, Donghyeon Jeon, Nayoung Choi, Gyu-Hwung Cho, Hwiyeol Jo, Changbong Kim, Hyunwoo Lee, Inho Kang, Sun Kim, Taiwoo Park
| Challenge: | Prior safety research on large language models focused on aligning them to safety requirements, but internalizing such safeguard features into larger models brought challenges of higher training cost and unintended degradation of helpfulness. |
| Approach: | They propose a multi-task learning mechanism that integrates harmful query detection and safeguard response into a single model. |
| Outcome: | The proposed approach outperforms the publicly available LLMs in harmful query detection and safeguard response generation. |
What Users Leave Unsaid: Under-Specified Queries Limit Vision-Language Models (2026.findings-acl)
Copied to clipboard
Dasol Choi, Guijin Son, Hanwool Lee, Minhyuk Kim, Hyunwoo Ko, Teabin Lim, Eungyeol Ahn, Jungwhan Kim, Seunghyeok Hong, Youngsook Song
| Challenge: | HAERAE-Vision benchmarks feature clear, explicit prompts but are often informal and underspecified . state-of-the-art models achieve under 50% on original queries, compared to GPT-5 and Gemini 2.5 Pro . |
| Approach: | They propose a benchmark of 653 real-world visual questions from Korean online communities . they find that even state-of-the-art models achieve under 50% on original queries . |
| Outcome: | HAERAE-Vision benchmarks from Korean online communities yield 1,306 query variants . state-of-the-art models achieve under 50% on original queries, compared with smaller models . authors show that query explicitation alone yields 8 to 22 point improvements . |
Taxonomy and Analysis of Sensitive User Queries in Generative AI Search System (2025.findings-naacl)
Copied to clipboard
Hwiyeol Jo, Taiwoo Park, Hyunwoo Lee, Nayoung Choi, Changbong Kim, Ohjoon Kwon, Donghyeon Jeon, Eui Hyeon Lee, Kyoungho Shin, Lim Sun Suk, Kyungmi Kim, Lee Jihye, Sun Kim
| Challenge: | generative LLMs have been used by industries for various purposes, but limited resources and limited experience hinder their deployment and maintenance. |
| Approach: | They propose a taxonomy for sensitive search queries and outline approaches to generating generative LLMs. |
| Outcome: | The proposed model can be used to analyze sensitive queries from real users. |
Large Language Models are Temporal and Causal Reasoners for Video Question Answering (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown remarkable performances on a wide range of natural language understanding and generation tasks. |
| Approach: | They propose a framework that exploits linguistic shortcuts and mitigates 'linguistic bias' by flipping the source pair and target label to understand their complex relationships. |
| Outcome: | The proposed framework outperforms both LLMs-based and non-LLMs- based models on five challenging VideoQA benchmarks. |
ZeroDL: Zero-shot Distribution Learning for Text Clustering via Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown impressive performance on downstream tasks, but if they cannot be fully described in prompts, they could fail to perform the task. |
| Approach: | They propose a method to contextualize a task toward a large language model (LLM) they use open-ended zero-shot inference from the entire dataset to aggregate the inference results and incorporate the aggregated meta-information for the actual task. |
| Outcome: | The proposed method improves text clustering tasks and improves on several datasets. |
Controlling Language Confusion in Multilingual LLMs (2025.acl-srw)
Copied to clipboard
| Challenge: | Large language models suffer from language confusion, a phenomenon in which responses are partially or entirely generated in unintended languages. |
| Approach: | They propose a supervised fine-tuning methodology which optimizes the likelihood of correct tokens without explicitly penalizing undesired outputs such as cross-lingual mixing. |
| Outcome: | The proposed model suppresses language-confused generation while maintaining strong language consistency even under high decoding temperatures while preserving general QA performance. |
XDetox: Text Detoxification with Token-Level Toxicity Explanations (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for mitigating toxic content are black-box approaches, which results in limitations in modifying toxic tokens. |
| Approach: | They propose a method that integrates token-level toxicity explanations with the masking and infilling detoxification processes. |
| Outcome: | The proposed method outperforms baseline methods in fluency and toxicity reduction. |