Papers by Joan Santoso
LLM Distillation for Efficient Few-Shot Multiple Choice Question Answering (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models excel at few-shot learning but their direct application in real-world scenarios is often hindered by their high computational cost. |
| Approach: | They propose a framework that uses Large Language Models for data generation and scoring to improve encoder model performance. |
| Outcome: | The proposed approach improves accuracy from 28.9% to 39.3% on a few-shot MCQA task . |
Ranking-Based Automatic Seed Selection and Noise Reduction for Weakly Supervised Relation Extraction (P18-2)
Copied to clipboard
| Challenge: | et al., 1998: bootstrapping for relation extraction uses minimally supervised methods . etudes show that proposed methods for automatic seed selection and noise reduction are better than baseline systems . |
| Approach: | They propose automatic seed selection and noise reduction for distantly supervised relation extraction tasks. |
| Outcome: | The proposed methods achieve better performance than baseline systems in both tasks. |
Pushing the Limits of Low-Resource NER Using LLM Artificial Data Generation (2024.findings-acl)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is an important task, but it requires a large amount of labeled data to perform well. |
| Approach: | They propose to use open-source Large Language Models to generate NER data with only a few labeled examples, reducing the cost of human annotations. |
| Outcome: | The proposed method significantly improves the baseline on diverse low-resource NER datasets and can be used to augment datasets with class-imbalance problems. |