Hansaem Kim

Prof. Hansaem Kim


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 December 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
XWXiaonan Wang
Xiaonan Wang
GCGyuri Choi
Gyuri Choi
SASubin An
Subin An
JKJoeun Kang
Joeun Kang
SPSeoyoon Park
Seoyoon Park
HKHansaem Kim
Hansaem Kim
As large language models (LLMs) improve in understanding and reasoning, they are increasingly used in privacy protection tasks such as de-identification, privacy-sensitive text generation, and entity obfuscation. However, these applications depend on an essential requirement: the accurate identification of personally identifiable information (PII). Compared with template-based PII that follows clear structural patterns, name-related PII depends much more on cultural and pragmatic context, which makes it harder for models to detect and raises higher privacy risks. Although recent studies begin to address this issue, existing work remains limited in language coverage, evaluation granularity, and the depth of error analysis. To address these gaps, this study proposes an error-driven framework that integrates diagnosis and intervention. Specifically, the framework introduces a method called Error-Driven Prompt (EDP), which transforms common failure patterns into executable prompting strategies. It further explores the integration of EDP with general advanced prompting techniques such as Chain-of-Thought (CoT), few-shot learning, and role-playing. In addition, the study constructed K-NameDiag, the first fine-grained evaluation benchmark for Korean name-related PII, which includes twelve culturally sensitive subtypes designed to examine model weaknesses in real-world contexts. The experimental results showed that EDP improved F1-scores in the range of 6 to 9 points across three widely used commercial LLMs, namely Claude Sonnet 4.5, GPT-5, and Gemini 2.5 Pro, while the Combined Enhanced Prompt (CEP), which integrates EDP with advanced prompting strategies, resulted in different shifts in precision and recall rather than consistent improvements. Further subtype-level analysis suggests that subtypes reliant on implicit cultural context remain resistant to correction, which shows the limitations of prompt engineering in addressing a model’s lack of internalized cultural knowledge.

31 December 2018
Verified
Journal Article
Open access
TBThe Korean Society Of Bilingualism
The Korean Society Of Bilingualism
JLJin Lee
Jin Lee
HKHansaem Kim
Hansaem Kim
The purpose of this paper is to analyze the utterance of Chinese Learners of Korean and to compare the aspects of fluency by proficiency and determine the features. Fluency is a very important factor to evaluate speaking skills, but there is no defined standard to evaluate fluency in Korean education field. Therefore, it is not easy to be consistent in applying evaluations. This study intended to analyze Chinese Korean learners’ verbal fluency shown in Korean Leaners’ Spoken Corpus based on evaluation qualities such as speech rate and pause and quantify the fluency evaluation. Speech rate quickened as proficiency improved, and the number of pauses decreased as proficiency improved. Especially, it was shown that the number of pauses sharply decreased as beginners advanced to intermediate level. Regarding the length of pause, ‘pauses of more than 1-second’ appeared more than ‘pauses of less than 1-second’ in Korean native speaker utterances. But ‘pauses of less than 1-second’ occupied about 70% of total number of pauses in Chinese Korean Learners utterances. In terms of the position of pause, as the proficiency improved, the number of pauses decreased in ‘within eojeol(word phrases unique in Korean language)’, ‘sentences boundaries’ and ‘clauses boundaries’. In addition, while the number of pauses appearing ‘between content word and function word’ and ‘within content words’ decreased, the number of pauses appearing ‘between function words’ rather increased.

3 June 2025 in arXiv
Verified
Preprint
Open access
PDF file
XWXiaonan Wang
Xiaonan Wang
BSBo Shao
Bo Shao
HKHansaem Kim
Hansaem Kim
Recent advances in vision-language models (VLMs) have enabled accurate image-based geolocation, raising serious concerns about location privacy risks in everyday social media posts. However, current benchmarks remain coarse-grained, linguistically biased, and lack multimodal and privacy-aware evaluations. To address these gaps, we present KoreaGEO Bench, the first fine-grained, multimodal geolocation benchmark for Korean street views. Our dataset comprises 1,080 high-resolution images sampled across four urban clusters and nine place types, enriched with multi-contextual annotations and two styles of Korean captions simulating real-world privacy exposure. We introduce a three-path evaluation protocol to assess ten mainstream VLMs under varying input modalities and analyze their accuracy, spatial bias, and reasoning behavior. Results reveal modality-driven shifts in localization precision and highlight structural prediction biases toward core cities.

21 March 2024 in arXiv
Verified
Preprint
Open access
PDF file
CCChangSu Choi
ChangSu Choi
YJYongbin Jeong
Yongbin Jeong
SPSeoyoon Park
Seoyoon Park
IWInHo Won
InHo Won
HLHyeonSeok Lim
HyeonSeok Lim
KLKyungTae Lim
KyungTae Lim
Large language models (LLMs) use pretraining to predict the subsequent word; however, their expansion requires significant computing resources. Numerous big tech companies and research institutes have developed multilingual LLMs (MLLMs) to meet current demands, overlooking less-resourced languages (LRLs). This study proposed three strategies to enhance the performance of LRLs based on the publicly available MLLMs. First, the MLLM vocabularies of LRLs were expanded to enhance expressiveness. Second, bilingual data were used for pretraining to align the high- and less-resourced languages. Third, a high-quality small-scale instruction dataset was constructed and instruction-tuning was performed to augment the LRL. The experiments employed the Llama2 model and Korean was used as the LRL, which was quantitatively evaluated against other developed LLMs across eight tasks. Furthermore, a qualitative assessment was performed based on human evaluation and GPT4. Experimental results showed that our proposed Bllossom model exhibited superior performance in qualitative analyses compared to previously proposed Korean monolingual models.