Papers by Sangmin Kim
Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to augment textual data are limited due to the discrete characteristics of the textual dataset. |
| Approach: | They propose a decision-boundary-aware data augmentation strategy to enhance robustness using pretrained language models by shifting latent features closer to the decision boundary and reconstruction to generate an ambiguous version with a soft label. |
| Outcome: | The proposed method performs better than existing methods and is extensible with curriculum data augmentation. |
A Few Bad Apples Spoil the Bunch: Preventing Global Entropy Collapse Driven by a Small Set of Tokens in LLM Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Reinforcement learning with verifiable rewards and Reinforced Learning from internal feedback fail to benefit from test-time compute due to entropy collapse and the resulting loss of reasoning diversity. |
| Approach: | They propose a strategy that assigns each generated token a redistribution score and applies selective KL regularization to only the top 5% of tokens under this score. |
| Outcome: | The proposed model improves on both RLVR and RLIF models on math reasoning benchmarks, showing that targeted entropy control at a vanishingly small subset of tokens is sufficient to sustain reasoning diversity and effective test-time scaling. |
HiKE: Hierarchical Evaluation Framework for Korean-English Code-Switching Speech Recognition (2026.findings-eacl)
Copied to clipboard
| Challenge: | Recent advances in automatic speech recognition (ASR) have pushed error rates below 5% on standard monolingual benchmarks. |
| Approach: | They propose a framework for the evaluation of multilingual ASR models using loanword labels and a hierarchical CS-level labeling scheme that allows for fine-tuning with synthetic CS data. |
| Outcome: | The proposed framework provides a means for the precise evaluation of multilingual ASR models and fosters research in the field. |
Don’t Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Vision Language Models suffer from hallucinations, attributing incorrect or misleading features to images. |
| Approach: | They propose a test-time approach that recalibrates the influence of blind tokens . they identify blind token by analyzing layer-wise attention distributions over image tokens. |
| Outcome: | The proposed approach reduces hallucinations in large vision language models . it uses a contrastive decoding strategy to balance the influence of blind tokens . |
Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL (2024.acl-long)
Copied to clipboard
Yunseon Choi, Sangmin Bae, Seonghyun Ban, Minchan Jeong, Chuheng Zhang, Lei Song, Li Zhao, Jiang Bian, Kee-Eung Kim
| Challenge: | Prompt tuning is an important technique for directing model behaviors and eliciting desired responses. |
| Approach: | They propose to find optimal prompt tokens using soft Q-learning to optimize models for prompt tuning. |
| Outcome: | The proposed method improves on baseline prompt tuning, and the results are more natural and interpretable. |
Carpe diem: On the Evaluation of World Knowledge in Lifelong Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Current language models are trained on static data, implying that the encoded knowledge could go wrong as time passes. |
| Approach: | They propose a temporally evolving question-answering benchmark for language models . they use Wikipedia databases to test language models for dynamic knowledge in ever-changing world . |
| Outcome: | The proposed task aims to model the evolution-adaptability of language models in the real world. |
Beyond Single-User Dialogue: Assessing Multi-User Dialogue State Tracking Capabilities of Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models have demonstrated remarkable performance in zero-shot dialogue state tracking (DST), reducing the need for task-specific training. |
| Approach: | They extend existing DST dataset by generating utterances of a second user based on speech act theory. |
| Outcome: | The proposed model incorporates utterances of a second user into conversations, enabling a controlled evaluation of LLMs in multi-user settings. |
AutoAugment Is What You Need: Enhancing Rule-based Augmentation Methods in Low-resource Regimes (2024.eacl-srw)
Copied to clipboard
| Challenge: | Existing methods for text data augmentation suffer from potential semantic damage due to the discrete nature of sentences. |
| Approach: | They propose to adapt AutoAugment to solve this problem by using softEDA to increase text data. |
| Outcome: | The proposed method can boost existing augmentation methods and enhance cutting-edge pretrained language models. |