Papers by Jaejin Lee
ArchCode: Incorporating Software Requirements in Code Generation with Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Despite the critical role of software requirements, these criteria have not been studied actively in previous code generation works. |
| Approach: | They propose a framework that leverages in-context learning to organize and extrapolate unexpressed requirements from textual descriptions. |
| Outcome: | The proposed framework generates functional requirements from textual descriptions and extrapolates unexpressed requirements from them. |
Thunder-NUBench: A Benchmark for LLMs’ Sentence-Level Negation Understanding (2026.findings-eacl)
Copied to clipboard
| Challenge: | Negation is a fundamental linguistic phenomenon that poses ongoing challenges for Large Language Models (LLMs) Current benchmarks treat negation as a minor detail within broader tasks, such as natural language inference. |
| Approach: | They propose a novel benchmark specifically created to assess sentence-level understanding of negation in Large Language Models (LLMs). |
| Outcome: | The proposed benchmark compares standard negation with structurally diverse alternatives, such as local negation, contradiction, and paraphrase. |
KLAAD: Refining Attention Mechanisms to Reduce Societal Bias in Generative Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models exhibit societal biases in their outputs, prompting ethical and societal challenges. |
| Approach: | They propose an attention-based debiasing framework that implicitly aligns attention distributions between stereotypical and anti-stereotypical sentence pairs without directly modifying model weights. |
| Outcome: | The proposed framework improves on BBQ and BOLD benchmarks while maintaining fluency and coherence. |
Assessing Socio-Cultural Alignment and Technical Safety of Sovereign LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent trends in LLMs development show growing interest in the use and application of sovereign LLM models. |
| Approach: | They propose a framework for extracting and evaluating socio-cultural elements of sovereign LLMs and assess their technical robustness. |
| Outcome: | The proposed framework assesses the socio-cultural elements of sovereign LLMs and their technical robustness. |
Thunder-DeID: Accurate and Efficient De-identification Framework for Korean Court Judgments (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study shows that the current de-identification process is inadequate for court judgments at scale . |
| Approach: | They propose a framework for de-identification that aligns with relevant laws and practices . they construct and release the first Korean legal dataset containing annotated judgments . |
| Outcome: | The proposed framework achieves state-of-the-art in the de-identification of court judgments. |
Thunder-KoNUBench: A Corpus-Aligned Benchmark for Korean Negation Understanding (2026.findings-acl)
Copied to clipboard
| Challenge: | Negation is a fundamental operation in natural language that reverses the meaning of an expression into its opposite. |
| Approach: | They propose a sentence-level negation understanding benchmark that measures negation performance in Korean. |
| Outcome: | The proposed benchmark improves negation understanding and broader comprehension in Korean. |
DuET: Dual Execution for Test Output Prediction with Generated Code and Pseudocode (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have shown that test output prediction is difficult to achieve due to code errors. |
| Approach: | They propose a framework that grounds prediction on error-resilient pseudocode and simulates execution via LLM reasoning to overcome limitations of direct execution suffering from code errors. |
| Outcome: | The proposed framework improves Pass@1 on LiveCodeBench, BigCodeBech-Hard, DevEval and HumanEval(+) and improves on pass@1 by 13.6 pp. |
PERC: Plan-As-Query Example Retrieval for Underrepresented Code Generation (2025.coling-main)
Copied to clipboard
| Challenge: | Using large language models to generate code has shown significant promise, but selecting effective examples to improve generation quality remains a challenging task. |
| Approach: | They propose a framework that utilizes algorithmic plans to identify and retrieve effective examples. |
| Outcome: | The proposed framework outperforms the state-of-the-art RAG methods in code generation even when the source and target languages match or differ. |
Generalizing Clinical De-identification Models by Privacy-safe Data Augmentation using GPT-4 (2024.emnlp-main)
Copied to clipboard
| Challenge: | De-identification (de-ID) is critical for patient confidentiality in clinical data management due to the difficulty of retaining training corpora and labeling standards vary across institutions. |
| Approach: | They propose to exploit GPT-4 for data augmentation through one-shot and zero-shot prompts to exploit the problem of PHI leakage by redacting PHI before processing. |
| Outcome: | The proposed approach significantly improves on three types of F1 scores in cross-dataset testing. |