Papers by Jinhee Jang
From Ground Trust to Truth: Disparities in Offensive Language Judgments on Contemporary Korean Political Discourse (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study using LLMs has relied on outdated datasets and limited generalization ability on unseen texts. |
| Approach: | They construct a large-scale dataset of political discourse and use it to make three judgments . they identify distinct patterns and demonstrate tendencies of label agreement using a leave-one-out strategy. |
| Outcome: | The proposed approach is applicable in real-world settings with inherent constraints. |
LLM Agents at the Roundtable: A Multi-Perspective and Dialectical Reasoning Framework for Essay Scoring (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a new framework for automated essay scoring is needed to achieve multi-perspective understanding and judgment. |
| Approach: | They propose a roundtable essay scoring framework that performs precise and human-aligned scoring under a zero-shot setting. |
| Outcome: | The proposed framework outperforms previous zero-shot AES approaches by enabling collaboration among agents with diverse evaluation perspectives. |
FairQE: Multi-Agent Framework for Mitigating Gender Bias in Translation Quality Estimation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing QE models exhibit systematic gender bias, especially in gender-ambiguous contexts. |
| Approach: | They propose a multi-agent-based, fairness-aware QE framework that mitigates gender bias in both gender-ambiguous and gender-explicit scenarios. |
| Outcome: | The proposed framework mitigates gender bias in gender-ambiguous and gender-explicit scenarios while maintaining the strengths of existing models. |
Plug-in and Fine-tuning: Bridging the Gap between Small Language Models and Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are renowned for their extensive linguistic knowledge and strong generalization capabilities, but their high computational demands make them unsuitable for resource-constrained environments. |
| Approach: | They propose a framework that integrates a single frozen layer from an LLM into a SLM and fine-tunes the combined model for specific tasks. |
| Outcome: | The proposed framework improves performance across a range of natural language processing tasks, including both natural language understanding and generation. |