Papers by Bojun Jin

3 papers
A Multi-persona Framework for Argument Quality Assessment (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for argument quality assessment do not consider multi-perspective evaluation due to subjective nature of arguments.
Approach: They propose a multi-persona framework for argument quality assessment that simulates diverse evaluator perspectives through large language models.
Outcome: The proposed framework outperforms baselines while providing comprehensive multi-perspective rationales on IBM-Rank-30k and IBM-ArgQ-5.3kArgs datasets.
Exploring Quality and Diversity in Synthetic Data Generation for Argument Mining (2025.emnlp-main)

Copied to clipboard

Challenge: Argument Mining (AM) is hindered by the scarcity of structure-annotated datasets, which are expensive to create manually.
Approach: They propose to use quality-oriented synthesis and diversity-oriented approach to generate argumentative texts with diverse topics and argument structures.
Outcome: The proposed approach significantly improves existing models in full-data and low-resource settings.
ArgGenBench: Benchmarking the Complex Controlled Argument Generation Capability of Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing studies focus on limited control signals such as topic, stance, length, style, strategy, audience, and key aspects, failing to capture this complexity.
Approach: They propose a benchmark that integrates multi-dimensional control into a single instruction to evaluate LLMs' ability to produce persuasive arguments.
Outcome: The proposed benchmarks show that existing models fail to capture multifaceted argumentative control signals.

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