Papers by Xiuzhen Zhang
DUCK: Rumour Detection on Social Media by Modelling User and Comment Propagation Networks (2022.naacl-main)
Copied to clipboard
| Challenge: | Social media rumours can cause significant economic and social disruption. |
| Approach: | They propose a rumour detection algorithm that leverages transformers and graph attention networks to jointly model social media conversations and the network of users who engaged in them. |
| Outcome: | The proposed algorithm produces superior performance over four widely used benchmark rumour datasets in English and Chinese. |
Prompted Aspect Key Point Analysis for Quantitative Review Summarization (2024.acl-long)
Copied to clipboard
| Challenge: | Recent abstractive approaches generate KPs based on sentences, resulting in overlapping and hallucinated opinions. |
| Approach: | They propose to use supervised learning to extract short sentences as key points before matching them to review comments for quantification of KP prevalence. |
| Outcome: | The proposed framework achieves state-of-the-art performance on Yelp and SPACE. |
Teaching Large Language Models Number-Focused Headline Generation With Key Element Rationales (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing studies focus only on textual quality and numerical accuracy for headline generation. |
| Approach: | They propose a framework for using rationales of key elements of Topic, Entities, and Numerical reasoning in news articles to enhance LLMs' ability to generate topic-aligned texts with precise numerical accuracy. |
| Outcome: | The proposed framework improves the ability of large language models to generate high-quality texts with precise numerical accuracy. |
Aspect-based Key Point Analysis for Quantitative Summarization of Reviews (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing studies on review summarization use only major opinions, but ignore minority opinions and fail to quantify opinion prevalence. |
| Approach: | They propose a framework for quantitative review summarization using aspect-based key point analysis (ABKPA) they use aspect-basic sentiment analysis to automatically annotate silver labels for matching aspect-sentiment pairs . |
| Outcome: | The proposed framework outperforms state-of-the-art baselines on Yelp reviews on five business categories. |
Task and Sentiment Adaptation for Appraisal Tagging (2023.eacl-main)
Copied to clipboard
| Challenge: | Appraisal framework in linguistics defines the framework for fine-grained evaluations and opinions. |
| Approach: | They propose to use language models to automatically identify and annotate text segments for appraisal. |
| Outcome: | The proposed model achieves superior performance than baseline adapter-based models and other neural classification models for cross-domain and cross-language settings. |
Cultural Bias Matters: A Cross-Cultural Benchmark Dataset and Sentiment-Enriched Model for Understanding Multimodal Metaphors (2025.acl-long)
Copied to clipboard
| Challenge: | Metaphors are pervasive in communication, making them crucial for natural language processing. |
| Approach: | They propose a multicultural multimodal metaphor dataset designed for cross-cultural studies of metaphor in Chinese and English. |
| Outcome: | The proposed model improves metaphor comprehension across cultural backgrounds and cultural domains. |
QQSUM: A Novel Task and Model of Quantitative Query-Focused Summarization for Review-based Product Question Answering (2025.acl-long)
Copied to clipboard
| Challenge: | Existing review-based product question answering systems generate only a single answer, ignoring the diversity of viewpoints. |
| Approach: | They propose a task which aims to summarize diverse customer opinions into representative Key Points and quantify their prevalence to effectively answer user queries. |
| Outcome: | The proposed task summarizes diverse customer opinions into representative Key Points and quantifies their prevalence to answer user queries. |
Neural Sparse Topical Coding (P18-1)
Copied to clipboard
| Challenge: | Topic models with sparsity enhancement are effective at learning discriminative and coherent latent topics of short texts. |
| Approach: | They propose a novel sparsity-enhanced topic model with back propagation that replaces the inference process with the back propagations, making it easy to explore extensions. |
| Outcome: | The proposed model outperforms existing methods on Web Snippet and 20Newsgroups datasets. |
Debiasing Large Language Models via Adaptive Causal Prompting with Sketch-of-Thought (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing prompting methods for Large Language Models (LLMs) suffer from excessive token usage and limited generalisability across diverse reasoning tasks. |
| Approach: | They propose an Adaptive Causal Prompting with Sketch-of-Thought framework that leverages structural causal models to infer the causal effect of a query on its answer. |
| Outcome: | The proposed framework outperforms existing prompting baselines in terms of accuracy, robustness, and computational efficiency. |
Less Is More? Examining Fairness in Pruned Large Language Models for Summarising Opinions (2025.emnlp-main)
Copied to clipboard
| Challenge: | reducing the size of LLMs through post-training pruning has been studied, but its impact on model fairness remains unexplored. |
| Approach: | They propose a pruning method that removes parameters that are redundant for input processing but influential in output generation. |
| Outcome: | The proposed pruning method can maintain or improve fairness across models and tasks where existing methods have limitations. |
Bias in Opinion Summarisation from Pre-training to Adaptation: A Case Study in Political Bias (2024.eacl-long)
Copied to clipboard
| Challenge: | Existing studies have focused on extractive summarisation but limited attention has been paid to abstractive summaries. |
| Approach: | They propose to trace bias in abstractive summarisation models to social media opinions using different models and adaptation methods. |
| Outcome: | The proposed model is compared with other models and adaptation methods to summarise social media opinions using different models and adaption methods. |
LMOD: A Large Multimodal Ophthalmology Dataset and Benchmark for Large Vision-Language Models (2025.findings-naacl)
Copied to clipboard
Zhenyue Qin, Yu Yin, Dylan Campbell, Xuansheng Wu, Ke Zou, Ninghao Liu, Yih Chung Tham, Xiuzhen Zhang, Qingyu Chen
| Challenge: | Existing benchmarks for large vision-language models (LVLMs) are limited to ophthalmology-specific applications. |
| Approach: | They introduce a large-scale multimodal ophthalmology benchmark consisting of 21,993 instances across five ocular imaging modalities and 13 state-of-the-art LVLM representatives from closed-source, open-source and medical domains. |
| Outcome: | The proposed model shows significant performance drop in ophthalmology compared to other domains. |
CMA-R: Causal Mediation Analysis for Explaining Rumour Detection (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing studies on explainable fake news or rumour detection by and large use attention weights as explanation, but the use of attention weighted explanations is problematic. |
| Approach: | They propose a causal mediation analysis approach to explain the decision-making process of neural models for rumour detection on Twitter by identifying salient tweets that explain model predictions and highlighting causally impactful words in the tweets. |
| Outcome: | The proposed approach shows strong agreement with human judgements for critical tweets determining the truthfulness of stories. |