Glyph Features Matter: A Multimodal Solution for EvaHan in LT4HALA2022

no code implementations • LT4HALA (LREC) 2022 • Wei Xinyuan, Liu Weihao, Qing Zong, Zhang Shaoqing, Baotian Hu

We participate in the LT4HALA2022 shared task EvaHan.

Data Augmentation Part-Of-Speech Tagging

Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?

1 code implementation • 30 May 2025 • Jiayu Liu, Qing Zong, Weiqi Wang, Yangqiu Song

These findings raise significant concerns about the reliability of epistemic markers for confidence estimation, underscoring the need for improved alignment between marker based confidence and actual model uncertainty.

Question Answering

AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora

1 code implementation • 29 May 2025 • Jiaxin Bai, Wei Fan, Qi Hu, Qing Zong, Chunyang Li, Hong Ting Tsang, Hongyu Luo, Yauwai Yim, Haoyu Huang, Xiao Zhou, Feng Qin, Tianshi Zheng, Xi Peng, Xin Yao, Huiwen Yang, Leijie Wu, Yi Ji, Gong Zhang, Renhai Chen, Yangqiu Song

We present AutoSchemaKG, a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas.

graph construction Knowledge Graphs

ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty

1 code implementation • 28 Dec 2024 • Qing Zong, Zhaowei Wang, Tianshi Zheng, Xiyu Ren, Yangqiu Song

In addition, to avoid possible semantic shortcuts, which is a severe problem of current LLMs study, we design a two-round method for knowledge robustness measurement utilizing both correctness and uncertainty.

KNOWCOMP POKEMON Team at DialAM-2024: A Two-Stage Pipeline for Detecting Relations in Dialogical Argument Mining

1 code implementation • 29 Jul 2024 • Zihao Zheng, Zhaowei Wang, Qing Zong, Yangqiu Song

Dialogical Argument Mining(DialAM) is an important branch of Argument Mining(AM).

Argument Mining Prediction

AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation

1 code implementation • 16 Feb 2024 • Zhaowei Wang, Wei Fan, Qing Zong, Hongming Zhang, Sehyun Choi, Tianqing Fang, Xin Liu, Yangqiu Song, Ginny Y. Wong, Simon See

Abstraction ability is crucial in human intelligence, which can also benefit various tasks in NLP study.

Instruction Following

TILFA: A Unified Framework for Text, Image, and Layout Fusion in Argument Mining

1 code implementation • 8 Oct 2023 • Qing Zong, Zhaowei Wang, Baixuan Xu, Tianshi Zheng, Haochen Shi, Weiqi Wang, Yangqiu Song, Ginny Y. Wong, Simon See

A main goal of Argument Mining (AM) is to analyze an author's stance.

Argument Mining Stance Classification