Papers by Seungmin Lee
REZE: Representation Regularization for Domain-adaptive Text Embedding Pre-finetuning (2026.acl-long)
Copied to clipboard
| Challenge: | Recent text embedding models often introduce task-induced bias alongside domain knowledge, leading to performance degradation. |
| Approach: | They propose a representation regularization framework that explicitly controls representation shift during embedding pre-finetuning. |
| Outcome: | The proposed framework outperforms standard pre-finetuning and isotropy-oriented post-hoc regularization in most settings. |
Topic-Guided Coherence Modeling for Sentence Ordering by Preserving Global and Local Information (D19-1)
Copied to clipboard
| Challenge: | Existing methods for sentence ordering are based on pairwise strategies. |
| Approach: | They propose a topic-guided coherence modeling (TGCM) for sentence ordering that utilizes sentence vectors in a permutation-invariant manner. |
| Outcome: | The proposed model outperforms state-of-the-art models from various perspectives. |
Late Code Chunking: A Code Chunking Strategy for Repository-Level Code Completion (2026.acl-short)
Copied to clipboard
| Challenge: | Despite significant advancements in Large Language Models (LLMs), repository-level code completion remains a challenging area. |
| Approach: | They propose a chunking strategy to improve the semantic understanding of code segments for Large Language Models. |
| Outcome: | The proposed strategy improves the semantic understanding of code segments for Large Language Models. |
Def-DTS: Deductive Reasoning for Open-domain Dialogue Topic Segmentation (2025.findings-acl)
Copied to clipboard
| Challenge: | Dialogue Topic Segmentation (DTS) suffers from data shortage, labeling ambiguity, and incremental complexity of recently proposed solutions. |
| Approach: | They propose a method that employs a structured prompting approach for context summarization, utterance intent classification, and deductive topic shift detection. |
| Outcome: | The proposed method outperforms traditional and state-of-the-art approaches in various dialogue settings. |