Hyunjae Kim
YOU?
Author Swipe
View article: Correction: Evaporation of Sn from Molten Fe–C–S Alloy Under Reduced Pressure at 1650 °C for Developing Sustainable Ferrous Scrap Recycling Process
Correction: Evaporation of Sn from Molten Fe–C–S Alloy Under Reduced Pressure at 1650 °C for Developing Sustainable Ferrous Scrap Recycling Process Open
View article: Correction: Evaporation of Cu from Molten Steel Containing C and S Under Reduced Pressure at 1650 °C for Developing Refining Process of EAF Steel
Correction: Evaporation of Cu from Molten Steel Containing C and S Under Reduced Pressure at 1650 °C for Developing Refining Process of EAF Steel Open
View article: Comparative Analysis of Multimodal Large Language Models GPT-4o and o1 vs Clinicians in Clinical Case Challenge Questions
Comparative Analysis of Multimodal Large Language Models GPT-4o and o1 vs Clinicians in Clinical Case Challenge Questions Open
SUMMARY Background Generative Pre-trained Transformer 4 (GPT-4) has demonstrated strong performance in standardized medical examinations but has limitations in real-world clinical settings. The newly released multimodal GPT-4o model, which…
View article: Evaporation of Sn from Molten Fe–C–S Alloy Under Reduced Pressure at 1650 $$^\circ $$C for Developing Sustainable Ferrous Scrap Recycling Process
Evaporation of Sn from Molten Fe–C–S Alloy Under Reduced Pressure at 1650 $$^\circ $$C for Developing Sustainable Ferrous Scrap Recycling Process Open
Electric arc furnace (EAF) steelmaking is emerging as a key low-carbon process for sustainable and large-scale steel production. Its successful implementation requires not only the development of environmentally friendly facilities but als…
View article: Evaporation of Cu from Molten Steel Containing C and S Under Reduced Pressure at 1650 °C for Developing Refining Process of EAF Steel
Evaporation of Cu from Molten Steel Containing C and S Under Reduced Pressure at 1650 °C for Developing Refining Process of EAF Steel Open
The evaporation of Cu from molten steel containing C and S was investigated by employing high-temperature gas–liquid reaction and kinetic mechanism analysis. To continue the development of the tramp element removal process by evaporation, …
View article: Rationale-Guided Retrieval Augmented Generation for Medical Question Answering
Rationale-Guided Retrieval Augmented Generation for Medical Question Answering Open
View article: Rationale-Guided Retrieval Augmented Generation for Medical Question Answering
Rationale-Guided Retrieval Augmented Generation for Medical Question Answering Open
Large language models (LLM) hold significant potential for applications in biomedicine, but they struggle with hallucinations and outdated knowledge. While retrieval-augmented generation (RAG) is generally employed to address these issues,…
View article: ETHIC: Evaluating Large Language Models on Long-Context Tasks with High Information Coverage
ETHIC: Evaluating Large Language Models on Long-Context Tasks with High Information Coverage Open
Recent advancements in large language models (LLM) capable of processing extremely long texts highlight the need for a dedicated evaluation benchmark to assess their long-context capabilities. However, existing methods, like the needle-in-…
View article: Dual‐Seed Strategy for High‐Performance Anode‐Less All‐Solid‐State Batteries
Dual‐Seed Strategy for High‐Performance Anode‐Less All‐Solid‐State Batteries Open
Interest in all‐solid‐state batteries (ASSBs), particularly the anode‐less type, has grown alongside the expansion of the electric vehicle (EV) market, because they offer advantages in terms of their energy density and manufacturing cost. …
View article: Augmenting Biomedical Named Entity Recognition with General-domain Resources
Augmenting Biomedical Named Entity Recognition with General-domain Resources Open
Training a neural network-based biomedical named entity recognition (BioNER) model usually requires extensive and costly human annotations. While several studies have employed multi-task learning with multiple BioNER datasets to reduce hum…
View article: Examine the Mediating Effect of Self-efficacy in Korean on the Relationship between Acculturative Stress and Learning Outcomes among International Students
Examine the Mediating Effect of Self-efficacy in Korean on the Relationship between Acculturative Stress and Learning Outcomes among International Students Open
본 연구의 목적은 외국인 유학생의 문화적응스트레스와 학습 성과의 관계에서 한국어자기효능감의 매개효과를 살펴보는 것이다. 이를 위해 중국, 베트남 국적의 어학연수생, 학부생 및 대학원생 365명을 대상으로 연구를 실시하였으며 연구문제를 중심으로 한 주요 연구 결과는 다음과 같다. 첫째, 유학생의 인구통계학적 특성에 따른 문화적응스트레스, 한국어자기효능감, 학습 성과의 차이를 분석한 결과 베트남 학생들의 문화적응스트레스가 더 높…
View article: CookingSense: A Culinary Knowledgebase with Multidisciplinary Assertions
CookingSense: A Culinary Knowledgebase with Multidisciplinary Assertions Open
This paper introduces CookingSense, a descriptive collection of knowledge assertions in the culinary domain extracted from various sources, including web data, scientific papers, and recipes, from which knowledge covering a broad range of …
View article: Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks
Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks Open
While recent advancements in commercial large language models (LM) have shown promising results in medical tasks, their closed-source nature poses significant privacy and security concerns, hindering their widespread use in the medical fie…
View article: A Study on Fire Detection Algorithm in ESS by Considering Fire Mechanism for Li-ion Battery
A Study on Fire Detection Algorithm in ESS by Considering Fire Mechanism for Li-ion Battery Open
정부의 녹색성장 및 탄소 중립 정책에 따라, 대용량 ESS(energy storage system)의 보급이 급속히 확산되고 있지만, 2017년 8월부터 시작된 ESS의 화재사고로 인하여 관련 업계가 큰 타격을 받고 있다. 이에 정부의 권고사항과 배터리 제조사의 화재대응 대책이 적용되고 있지만, 여전히 ESS의 화재가 발생하고 있다. 한편, ESS의 화재는 한번 발생하면 쉽게 진압되기 어렵고, 대규모 화재로 이어질 가능성이 …
View article: Comment on egusphere-2023-1747
Comment on egusphere-2023-1747 Open
Abstract. The high spatial resolution NO2 vertical column densities (VCDs) were measured from the airborne observations using the low-cost Hyperspectral Imaging Sensor (HIS) at three industrial areas (i.e., Chun…
View article: Multiplex PCR detection method of genetically modified canola event (MON94100, LBFLFK, and NS-B50027-4) combined with capillary electrophoresis
Multiplex PCR detection method of genetically modified canola event (MON94100, LBFLFK, and NS-B50027-4) combined with capillary electrophoresis Open
View article: LIQUID: A Framework for List Question Answering Dataset Generation
LIQUID: A Framework for List Question Answering Dataset Generation Open
Question answering (QA) models often rely on large-scale training datasets, which necessitates the development of a data generation framework to reduce the cost of manual annotations. Although several recent studies have aimed to generate …
View article: Comparative Evaluation of Culture Media for Quantification of Lactic Acid Bacteria in Various Dairy Products
Comparative Evaluation of Culture Media for Quantification of Lactic Acid Bacteria in Various Dairy Products Open
Dairy products are extensively used as carriers of probiotic strains that have potential health benefits.Assessment of the viability of probiotic strains during manufacturing is important to ensure that products meet recommended levels.Hen…
View article: LIQUID: A Framework for List Question Answering Dataset Generation
LIQUID: A Framework for List Question Answering Dataset Generation Open
Question answering (QA) models often rely on large-scale training datasets, which necessitates the development of a data generation framework to reduce the cost of manual annotations. Although several recent studies have aimed to generate …
View article: Automatic Creation of Named Entity Recognition Datasets by Querying Phrase Representations
Automatic Creation of Named Entity Recognition Datasets by Querying Phrase Representations Open
Most weakly supervised named entity recognition (NER) models rely on domain-specific dictionaries provided by experts. This approach is infeasible in many domains where dictionaries do not exist. While a phrase retrieval model was used to …
View article: Automatic Creation of Named Entity Recognition Datasets by Querying Phrase Representations
Automatic Creation of Named Entity Recognition Datasets by Querying Phrase Representations Open
Most weakly supervised named entity recognition (NER) models rely on domain-specific dictionaries provided by experts. This approach is infeasible in many domains where dictionaries do not exist. While a phrase retrieval model was used to …
View article: Differentiating between Enterococcusfaecium and Enterococcuslactis by Matrix-Assisted Laser Desorption Ionization Time-of-Flight Mass Spectrometry
Differentiating between Enterococcusfaecium and Enterococcuslactis by Matrix-Assisted Laser Desorption Ionization Time-of-Flight Mass Spectrometry Open
Unlike Enterococcus faecium strains, some Enterococcus lactis strains are considered potential probiotic strains as they lack particular virulence and antibiotic resistance genes. However, these closely related species are difficult to dis…
View article: Simple Questions Generate Named Entity Recognition Datasets
Simple Questions Generate Named Entity Recognition Datasets Open
Recent named entity recognition (NER) models often rely on human-annotated datasets requiring the vast engagement of professional knowledge on the target domain and entities. This work introduces an ask-to-generate approach, which automati…
View article: Simple Questions Generate Named Entity Recognition Datasets
Simple Questions Generate Named Entity Recognition Datasets Open
Recent named entity recognition (NER) models often rely on human-annotated datasets, requiring the significant engagement of professional knowledge on the target domain and entities. This research introduces an ask-to-generate approach tha…
View article: Improving Tagging Consistency and Entity Coverage for Chemical Identification in Full-text Articles
Improving Tagging Consistency and Entity Coverage for Chemical Identification in Full-text Articles Open
This paper is a technical report on our system submitted to the chemical identification task of the BioCreative VII Track 2 challenge. The main feature of this challenge is that the data consists of full-text articles, while current datase…
View article: How Do Your Biomedical Named Entity Models Generalize to Novel Entities
How Do Your Biomedical Named Entity Models Generalize to Novel Entities Open
The number of biomedical literature on new biomedical concepts is rapidly increasing, which necessitates a reliable biomedical named entity recognition (BioNER) model for identifying new and unseen entity mentions. However, it is questiona…
View article: Unexplored volatile organic compound emitted from petrochemical facilities: implications for ozone production and atmospheric chemistry
Unexplored volatile organic compound emitted from petrochemical facilities: implications for ozone production and atmospheric chemistry Open
A compound was observed using airborne proton transfer reaction time-of-flight mass spectrometry (PTR-TOF-MS) measurements in the emission plumes from the Daesan petrochemical facility in South Korea. The compound was detected at m/z 43.01…
View article: Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering
Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering Open
One of the main challenges in conversational question answering (CQA) is to resolve the conversational dependency, such as anaphora and ellipsis. However, existing approaches do not explicitly train QA models on how to resolve the dependen…
View article: "Killing Me" Is Not a Spoiler: Spoiler Detection Model using Graph Neural Networks with Dependency Relation-Aware Attention Mechanism
"Killing Me" Is Not a Spoiler: Spoiler Detection Model using Graph Neural Networks with Dependency Relation-Aware Attention Mechanism Open
Several machine learning-based spoiler detection models have been proposed recently to protect users from spoilers on review websites. Although dependency relations between context words are important for detecting spoilers, current attent…
View article: “Killing Me” Is Not a Spoiler: Spoiler Detection Model using Graph Neural Networks with Dependency Relation-Aware Attention Mechanism
“Killing Me” Is Not a Spoiler: Spoiler Detection Model using Graph Neural Networks with Dependency Relation-Aware Attention Mechanism Open
Several machine learning-based spoiler detection models have been proposed recently to protect users from spoilers on review websites. Although dependency relations between context words are important for detecting spoilers, current attent…