Papers by Xinyu Pang
Subjective Topic meets LLMs: Unleashing Comprehensive, Reflective and Creative Thinking through the Negation of Negation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) exhibit powerful reasoning capacity, but their evaluation still lacks comprehensiveness. |
| Approach: | They propose a framework grounded in the principle of the Negation of Negation (NeoN) to unleash the potential comprehensive, reflective, and creative thinking abilities of LLMs. |
| Outcome: | The proposed framework unleashes the potential comprehensive, reflective, and creative thinking abilities of large language models. |
A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing models of large language models struggle with complex logical reasoning problems. |
| Approach: | They propose to use large language models to identify their own errors to improve their models' performance. |
| Outcome: | The proposed models can identify logical fallacies accurately and improve by themselves. |
Assimilation and Accommodation: Task-Adaptive Hierarchical Abstraction for Solving Web Tasks (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods focus on summarizing workflows, i.e., common sub-routines, which introduce excessive low-level details that distract models. |
| Approach: | They propose a framework that derives task-adaptive hierarchical abstraction from experience to enhance web task reasoning. |
| Outcome: | The proposed framework improves performance with competitive cost-efficiency on Mind2web and Webarena. |
Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models (2025.coling-main)
Copied to clipboard
Xinyu Pang, Ruixin Hong, Zhanke Zhou, Fangrui Lv, Xinwei Yang, Zhilong Liang, Bo Han, Changshui Zhang
| Challenge: | Existing large language models (LLMs) fail due to lack of knowledge or incorrect knowledge application. |
| Approach: | They propose a knowledge-augmented framework that constructs a formula set to provide explicit physics knowledge and utilizes checklists to guide effective knowledge application. |
| Outcome: | The proposed framework achieves state-of-the-art performance on SciBench with an average accuracy improvement of 5.8%. |