Papers by Congbo Ma
Text is All You Need: LLM-enhanced Incremental Social Event Detection (2025.acl-long)
Copied to clipboard
| Challenge: | Existing state-of-the-art (SOTA) SED models rely on graph neural networks (GNNs) Existing SED frameworks rely heavily on GNNs, which require complex graph construction and time-consuming training processes. |
| Approach: | They propose a framework that leverages the rich background knowledge of large language models to formalize and disambiguate short texts by completing abbreviations and summarizing informal expressions. |
| Outcome: | The proposed framework outperforms existing models on two challenging real-world datasets. |
An Empirical Study on Topic Preservation in Multi-Document Summarization (2022.aacl-srw)
Copied to clipboard
| Challenge: | Multi-document summarization is a process of generating an informative and concise summary from multiple topic-related documents. |
| Approach: | They perform empirical analysis on two MDS datasets and study topic preservation on generated summaries from 8 MDS models. |
| Outcome: | The results show that extractive and abstractive summarization methods preserve topic information from source documents. |
Explicit and Implicit Data Augmentation for Social Event Detection (2025.acl-long)
Copied to clipboard
| Challenge: | Social event detection relies on labeled data, but annotation is costly and labor-intensive. |
| Approach: | They propose a plug-and-play dual augmentation framework that combines explicit text-based and implicit feature-space augmentation to enhance data diversity and model robustness. |
| Outcome: | The proposed framework outperforms the best baseline model by 17.67% on the Twitter2012 dataset and 15.57% on the twitter2018 dataset in terms of the average F1 score. |
HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | Hallucination is a significant challenge for large language models, but current methods struggle when non-factual information arises in the early or mid-sequence of outputs, reducing their reliability. |
| Approach: | They propose a method that captures the full dynamics of large language models by using neural differential equations to assess the truthfulness of statements. |
| Outcome: | The proposed method achieves 14% improvement in AUC-ROC on the True-False dataset compared to state-of-the-art methods. |
MedErrBench: A Fine-Grained Multilingual Benchmark for Medical Error Detection and Correction with Clinical Expert Annotations (2026.findings-acl)
Copied to clipboard
Congbo Ma, Yichun Zhang, Yousef Al-Jazzazi, Ahamed Foisal, Laasya Sharma, Yousra Sadqi, Khaled Saleh, Jihad Mallat, Farah E. Shamout
| Challenge: | Existing or generated clinical text may contain inaccuracies that can lead to serious adverse outcomes. |
| Approach: | They introduce a multilingual benchmark for error detection, localization and correction . they assessed the performance of a range of general-purpose, language-specific, and medical-domain language models . |
| Outcome: | The proposed benchmark covers English, Arabic and Chinese, with natural medical cases annotated and reviewed by domain experts. |
Learning From the Source Document: Unsupervised Abstractive Summarization (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for abstractive summarization are under supervised training, but obtaining high-quality and large-scale datasets for supervised learning is laboriously difficult. |
| Approach: | They propose an unsupervised method that leverages contrastive learning to generate summaries by rewriting and paraphrasing the source documents to generate good summary. |
| Outcome: | The proposed method outperforms baseline methods on extensive experiments on source documents and fake documents. |