Papers by Yungi Kim
LP Data Pipeline: Lightweight, Purpose-driven Data Pipeline for Large Language Models (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Creating high-quality datasets for large language models often relies on resource-intensive, GPU-accelerated models for quality filtering, making the process time-consuming and costly. |
| Approach: | They propose a framework that operates entirely on CPUs to streamline the processes of dataset extraction, filtering, and curation. |
| Outcome: | The proposed framework reduces preparation time and costs while maintaining high data quality while enhancing the applicability of LLMs in specialized contexts. |
Evalverse: Unified and Accessible Library for Large Language Model Evaluation (2024.emnlp-demo)
Copied to clipboard
| Challenge: | Evalverse is a library that unifies disparate evaluation tools into a single, user-friendly framework. |
| Approach: | They propose to integrate existing evaluation frameworks into a single, user-friendly framework that enables individuals with limited knowledge of artificial intelligence to request LLM evaluations and receive detailed reports. |
| Outcome: | The proposed framework can be used by individuals with limited knowledge of artificial intelligence to request and receive LLM evaluations and receive detailed reports. |
Open Ko-LLM Leaderboard: Evaluating Large Language Models in Korean with Ko-H5 Benchmark (2024.acl-long)
Copied to clipboard
Chanjun Park, Hyeonwoo Kim, Dahyun Kim, SeongHwan Cho, Sanghoon Kim, Sukyung Lee, Yungi Kim, Hwalsuk Lee
| Challenge: | Existing benchmarks for evaluating Large Language Models are limited to the English language. |
| Approach: | They introduce the Open Ko-LLM Leaderboard and Ko-H5 Benchmark as tools for evaluating Large Language Models in Korean using private test sets. |
| Outcome: | The proposed evaluation framework is well integrated in the Korean LLM community. |
Representing the Under-Represented: Cultural and Core Capability Benchmarks for Developing Thai Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Rapid advancements in large language models have highlighted the need for robust evaluation frameworks that assess their core capabilities. |
| Approach: | They propose two benchmarks to assess core capabilities of large language models . current benchmarks for Thai focus mainly on traditional NLP tasks . |
| Outcome: | The proposed benchmarks are based on evaluations of various LLMs with multi-lingual capabilities and are publicly available to encourage further research and development for Thai LLM. |
Rethinking KenLM: Good and Bad Model Ensembles for Efficient Text Quality Filtering in Large Web Corpora (2025.acl-short)
Copied to clipboard
| Challenge: | Existing methods to efficiently filter large web corpora require GPU resources. |
| Approach: | They propose an ensemble approach that leverages two contrasting KenLMs to filter large web corpora. |
| Outcome: | The proposed method significantly reduces noisy content while preserving high-quality content compared to the traditional KenLM training method. |
Open Ko-LLM Leaderboard2: Bridging Foundational and Practical Evaluation for Korean LLMs (2025.naacl-industry)
Copied to clipboard
| Challenge: | Open Ko-LLM Leaderboard has been instrumental in benchmarking Korean Large Language Models . however, the leaderboard has faced significant limitations over time due to its academic nature . |
| Approach: | They propose an improved version of the Open Ko-LLM Leaderboard to improve benchmarking . original benchmarks replaced with new tasks that align with real-world capabilities . four new native Korean benchmarks are introduced to better reflect distinct characteristics of Korean language . |
| Outcome: | The proposed framework improves the Open Ko-LLM Leaderboard2 benchmark suite. |
sDPO: Don’t Use Your Data All at Once (2025.coling-industry)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly requiring precision and accuracy in alignment tuning. |
| Approach: | They propose a stepwise DPO technique that partitions available preference datasets incrementally rather than utilizing entire dataset simultaneously. |
| Outcome: | The proposed technique improves the accuracy of reference models and the overall performance of the final model. |
SAAS: Solving Ability Amplification Strategy for Enhanced Mathematical Reasoning in Large Language Models (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Existing approaches to enhance mathematical reasoning and problem-solving abilities of Large Language Models (LLMs) despite their remarkable performance across domains, a notable challenge persists in the realm of mathematical reasoning. |
| Approach: | They propose a sequential learning approach that integrates the Chain-of-Thought and the Program-ofThough. |
| Outcome: | The proposed approach achieves state-of-the-art (SOTA) performance by integrating CoT and PoT learning. |