Papers by Yajing Xu
RCL: Relation Contrastive Learning for Zero-Shot Relation Extraction (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches to extract relations require large-scale labeled data. |
| Approach: | They propose a Relation Contrastive Learning framework to mitigate similar relations and similar entities problems by optimizing a contrastive instance loss with a relation classification loss on seen relations. |
| Outcome: | The proposed framework can learn subtle difference between instances and achieve better separation between different relation categories in the representation space simultaneously. |
Self-Guided Function Calling in Large Language Models via Stepwise Experience Recall (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for function calling require expert effort and prompt engineering becomes inefficient. |
| Approach: | They propose a method that performs fine-grained, stepwise retrieval from a continually updated experience pool. |
| Outcome: | The proposed method achieves an average improvement of 6.1% on easy and 4.7% on hard questions. |
Have We Designed Generalizable Structural Knowledge Promptings? Systematic Evaluation and Rethinking (2025.acl-long)
Copied to clipboard
Yichi Zhang, Zhuo Chen, Lingbing Guo, Yajing Xu, Shaokai Chen, Mengshu Sun, Binbin Hu, Zhiqiang Zhang, Lei Liang, Wen Zhang, Huajun Chen
| Challenge: | Existing methods to integrate external knowledge into LLMs focus on specific problems, lacking a comprehensive exploration of the generalization and capability boundaries of SKP. |
| Approach: | They propose a new paradigm for structural knowledge prompting to integrate external structural knowledge into LLMs by incorporating structural representations. |
| Outcome: | The proposed benchmark SUBARU enables the evaluation of the generalization capabilities of SKP from four perspectives. |
Learning Discriminative Representations for Open Relation Extraction with Instance Ranking and Label Calibration (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to extract relational facts without pre-defined relation types cluster hard or semi-hard instances into the same relation type. |
| Approach: | They propose a method to learn discriminative representations for open relation extraction by using instance ranking and label calibration strategies. |
| Outcome: | The proposed method outperforms existing methods on two public datasets. |
Cluster-aware Pseudo-Labeling for Supervised Open Relation Extraction (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods to extract novel relations do not achieve effective knowledge transfer . experimental results show that the proposed method is state-of-the-arts . |
| Approach: | They propose a Cluster-aware Pseudo-Labeling method to improve pseudo-labels quality . they firstly pre-trained the relation models with pre-defined relations to learn them . |
| Outcome: | The proposed method improves the pseudo-labels quality and transfer more knowledge for discovering novel relations. |
Learning to Rank Utterances for Query-Focused Meeting Summarization (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to generate a generic summary for meetings are limited due to the conflict between long meetings and limited input size. |
| Approach: | They propose a Ranker-Generator framework that learns to rank utterances by comparing them in pairs and learning from the global orders, then uses top utterrances as the generator’s input. |
| Outcome: | The proposed model outperforms existing models with fewer parameters due to the conflict between long meetings and limited input size. |