Papers by Eunhyeok Park
PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to decode early exit logits in large language models are lacking in factuality and accuracy. |
| Approach: | They propose a contrastive decoding method that constructs the amateur model via layer pruning rather than early exit. |
| Outcome: | The proposed method improves factuality with minimal inference overhead and is robust and practical. |
QEFT: Quantization for Efficient Fine-Tuning of LLMs (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to optimize inference and fine-tuning for large language models have failed to improve all aspects of the process. |
| Approach: | They propose a new technique that accelerates both inference and fine-tuning while using fewer resources. |
| Outcome: | The proposed technique accelerates both inference and fine-tuning while using fewer resources. |
Efficient Latent Semantic Clustering for Scaling Test-Time Computation of LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for scaling test-time computation rely on external models that introduce substantial computational overhead and fail to capture context-aware semantics. |
| Approach: | They propose a method that leverages the generator LLM’s internal hidden states for clustering, eliminating the need for external models. |
| Outcome: | The proposed method improves the computational efficiency of test-time scaling while maintaining or exceeding the performance of existing methods. |
SEAL: Scaling to Emphasize Attention for Long-Context Retrieval (2025.acl-long)
Copied to clipboard
| Challenge: | Recent studies show that advanced LLMs suffer from degradation when processing longer context data. |
| Approach: | They propose a learning-based mechanism that leverages generated data to emphasize attention heads for long-context retrieval. |
| Outcome: | The proposed approach improves retrieval performance over long contexts while maintaining high reliability. |
AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Weight-only quantization is a powerful optimization technique for large language models . pushing below 4 bits often leads to substantial accuracy degradation due to increased quantization error. |
| Approach: | They propose a framework that assigns layer-wise quantization bit-widths to optimize model quality and memory usage. |
| Outcome: | The proposed framework can optimize for large language models under memory constraints. |