Papers by Mujeen Sung

Rationale-Guided Retrieval Augmented Generation for Medical Question Answering (2025.naacl-long)

Copied to clipboard

Jiwoong Sohn, Yein Park, Chanwoong Yoon, Sihyeon Park, Hyeon Hwang, Mujeen Sung, Hyunjae Kim, Jaewoo Kang

Challenge:	Large language models (LLMs) struggle with hallucinations and outdated knowledge.
Approach:	They propose a retrieval-augmented generation framework for enhancing the reliability of RAG in biomedical contexts.
Outcome:	The proposed framework outperforms the previous best medical RAG model by up to 5.6% across three medical question-answering benchmarks.

Learning Dense Representations of Phrases at Scale (2021.acl-long)

Copied to clipboard

Jinhyuk Lee, Mujeen Sung, Jaewoo Kang, Danqi Chen

Information Retrieval

Challenge:	Existing phrase retrieval models rely on sparse representations and still underperform retriever-reader approaches.
Approach:	They propose a method to learn phrase representations from reading comprehension tasks using negative sampling methods.
Outcome:	The proposed model improves over previous models by 15%-25% absolute accuracy and matches the performance of state-of-the-art retrieval models.

Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification (2023.emnlp-main)

Copied to clipboard

Mujeen Sung, James Gung, Elman Mansimov, Nikolaos Pappas, Raphael Shu, Salvatore Romeo, Yi Zhang, Vittorio Castelli

Language Models

Challenge:	Existing methods for IC training do not provide sufficient examples for each intent . a novel pre-training method is proposed to provide a better understanding of intents .
Approach:	They propose a method that uses contrastive learning with intent psuedo-labels to produce embeddings that are well-suited for IC tasks.
Outcome:	The proposed method achieves 5.4% and 4.0% higher accuracy than the current state-of-the-art method on four IC datasets.

Learning from Negative Samples in Biomedical Generative Entity Linking (2025.findings-acl)

Copied to clipboard

Chanhwi Kim, Hyunjae Kim, Sihyeon Park, Jiwoo Lee, Mujeen Sung, Jaewoo Kang

Semantic Text Processing

Challenge:	Generative models are usually trained only with positive samples and do not explicitly learn from hard negative samples, which are entities that look similar but have different meanings.
Approach:	They propose a framework that trains generative BioEL models using negative samples to learn from hard negative samples.
Outcome:	The proposed framework outperforms baseline models by up to an average top-1 accuracy of 1.4% on five benchmarks.

CookingSense: A Culinary Knowledgebase with Multidisciplinary Assertions (2024.lrec-main)

Copied to clipboard

Donghee Choi, Mogan Gim, Donghyeon Park, Mujeen Sung, Hyunjae Kim, Jaewoo Kang, Jihun Choi

Semantic Text Processing

Challenge:	CookingSense is a descriptive collection of knowledge assertions in the culinary domain extracted from various sources, including web data, scientific papers, and recipes.
Approach:	They introduce CookingSense, a descriptive collection of knowledge assertions in the culinary domain extracted from various sources, including web data, scientific papers, and recipes.
Outcome:	The proposed system improves retrieval augmented language models and food decision support systems.

Adversarial Subword Regularization for Robust Neural Machine Translation (2020.findings-emnlp)

Copied to clipboard

Jungsoo Park, Mujeen Sung, Jinhyuk Lee, Jaewoo Kang

Multilinguality

Challenge:	Existing methods for segmenting words into subword units are not robust enough to handle multiple subword candidates.
Approach:	They propose to regularize subword segmentations that maximize the translation loss by using gradient signals during training to prevent erroneous segmentations of unseen words.
Outcome:	The proposed method improves the performance of NMT models on low-resource and out-domain datasets.

Can Language Models be Biomedical Knowledge Bases? (2021.emnlp-main)

Copied to clipboard

Mujeen Sung, Jinhyuk Lee, Sean Yi, Minji Jeon, Sungdong Kim, Jaewoo Kang

Semantic Text Processing

Challenge:	Existing studies have focused on probing LMs in the general domain but little attention has been given to whether they can be used as domain knowledge bases.
Approach:	They propose to use 49K biomedical factual knowledge triples to probe LMs for biomedically . they find that biomedic LM can achieve up to 18.51% Acc@5 on retrieving biomedcial knowledge.
Outcome:	The proposed biomedical factual knowledge probing benchmark achieves 18.51% Acc@5 on biomedically-relevant knowledge retrieval.

Optimizing Test-Time Query Representations for Dense Retrieval (2023.findings-acl)

Copied to clipboard

Mujeen Sung, Jungsoo Park, Jaewoo Kang, Danqi Chen, Jinhyuk Lee

Semantic Text Processing

Challenge:	Recent developments of dense retrieval rely on quality representations of queries and contexts from pre-trained query and context encoders.
Approach:	They propose a test-time optimization of query representations that provides fine-grained pseudo labels over retrieval results.
Outcome:	The proposed algorithm improves open-domain question answering accuracy and direct re-ranking by up to 2.0% while running 1.3–2.4x faster with an efficient implementation.

Biomedical Entity Representations with Synonym Marginalization (2020.acl-main)

Copied to clipboard

Mujeen Sung, Hwisang Jeon, Jinhyuk Lee, Jaewoo Kang

Representation Learning

Challenge:	Biomedical named entities are often used as key features in biomedical text mining.
Approach:	They propose to use a model-based candidate selection to maximize the marginal likelihood of the synonyms present in top candidates.
Outcome:	The proposed model outperforms previous state-of-the-art models on four biomedical entity normalization datasets with three different entity types.

Open Your Model’s Eyes: Video and Context-Aware Multimodal Backchannel Prediction (2026.acl-long)

Copied to clipboard

Min-Jae Kim, Jun-Yeong Moon, Mujeen Sung, Gyeong-Moon Park

Multimodality

Challenge:	Existing methods for predicting backchannels rely on audio and text . existing methods omit visual cues and conversational contexts for accurate prediction .
Approach:	They propose a framework that leverages visual cues and conversational contexts to enhance backchannel prediction.
Outcome:	The proposed framework outperforms existing methods and simple multimodal baselines in recognizing complex backchannels such as empathy.

Structured List-Grounded Question Answering (2025.coling-main)

Copied to clipboard

Mujeen Sung, Song Feng, James Gung, Raphael Shu, Yi Zhang, Saab Mansour

Natural Language Interfaces

Challenge:	Document-grounded dialogue systems aim to answer user queries by leveraging external information.
Approach:	They propose a dataset to evaluate QA systems' ability to interpret and use structured lists . they use language models and model-based filtering processes to enhance data quality .
Outcome:	The proposed model outperforms baselines on the LIST2QA dataset . it shows that the proposed model is more accurate and complete than baselines .