Papers by Jinhee Jang

4 papers
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Challenge: a recent study using LLMs has relied on outdated datasets and limited generalization ability on unseen texts.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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations