Chao Wang
Chao Wang has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Fengbin Zhu
National University of Singapore, Singapore, Singapore
5 shared publications - Fuli Feng
National University of Singapore, Singapore, Singapore
5 shared publications - Tat-Seng Chua
National University of Singapore, Singapore, Singapore
5 shared publications - Huanbo Luan
ESTATES PTE LTD, Singapore, Singapore
3 shared publications - Moxin Li
National University of Singapore, Singapore, Singapore
2 shared publications - Wenjie Wang
National University of Singapore, Singapore, Singapore
2 shared publications
Latest Publications
- Top Cited Papers
- 17 February 2026
- Published by Springer Nature
- p. 74-88
MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding and Grounding
- 17 February 2026
- Published by Springer Nature
- p. 74-88
Top Cited PapersMMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding and Grounding
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 6289-6297
Towards Temporal-Aware Multi-Modal Retrieval Augemented Generation in Finance
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 6289-6297
Open AccessTowards Temporal-Aware Multi-Modal Retrieval Augemented Generation in Finance
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4184-4187
FinIR: The 2nd Workshop on Financial Information Retrieval in the Era of Generative AI
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4184-4187
Open AccessFinIR: The 2nd Workshop on Financial Information Retrieval in the Era of Generative AI
- Open Access
- 14 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 310-318
TAT-LLM: A Specialized Language Model for Discrete Reasoning over Financial Tabular and Textual Data
In this work, we develop a specialized language model with strong discrete reasoning capabilities to tackle question answering (QA) over hybrid tabular and textual data in finance. Compared with adopting online LLMs, specializing smaller LLMs is more advantageous in response to users’ concerns about cost, network latency, and data security risks. To this end, we first abstract a Step-wise Pipeline for tabular and textual QA to help LLMs better execute multi-step inference, which includes three key steps, i.e. Extractor, Reasoner and Executor. This pipeline is proved to bring great performance grains compared with applying other prompting strategies like Chain-of-Thought (CoT), and meanwhile provides better interpretability to the derivation of the answer, with fixed inference steps and intermediate outcomes as references. We then develop a TAT-LLM model by fine-tuning LLaMA 2 with the training data generated automatically from existing datasets following the Step-wise Pipeline. The experimental results have verified that our TAT-LLM model can outperform all compared models, including prior best fine-tuned models and very large-scale LLMs like GPT-4 on FinQA, TAT-QA and TAT-DQA benchmarks. It is hoped that this work will shed light on practical solutions to the intelligent understanding of financial documents in the future. The generated datasets and trained models will be made publicly available to facilitate future research on the development of financial LLMs.
- 14 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 310-318
Open AccessTAT-LLM: A Specialized Language Model for Discrete Reasoning over Financial Tabular and Textual Data
In this work, we develop a specialized language model with strong discrete reasoning capabilities to tackle question answering (QA) over hybrid tabular and textual data in finance. Compared with adopting online LLMs, specializing smaller LLMs is more advantageous in response to users’ concerns about cost, network latency, and data security risks. To this end, we first abstract a Step-wise Pipeline for tabular and textual QA to help LLMs better execute multi-step inference, which includes three key steps, i.e. Extractor, Reasoner and Executor. This pipeline is proved to bring great performance grains compared with applying other prompting strategies like Chain-of-Thought (CoT), and meanwhile provides better interpretability to the derivation of the answer, with fixed inference steps and intermediate outcomes as references. We then develop a TAT-LLM model by fine-tuning LLaMA 2 with the training data generated automatically from existing datasets following the Step-wise Pipeline. The experimental results have verified that our TAT-LLM model can outperform all compared models, including prior best fine-tuned models and very large-scale LLMs like GPT-4 on FinQA, TAT-QA and TAT-DQA benchmarks. It is hoped that this work will shed light on practical solutions to the intelligent understanding of financial documents in the future. The generated datasets and trained models will be made publicly available to facilitate future research on the development of financial LLMs.
- Open Access
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1236-1244
SoarGraph: Numerical Reasoning over Financial Table-Text Data via Semantic-Oriented Hierarchical Graphs
Towards the intelligent understanding of table-text data in the finance domain, previous research explores numerical reasoning over table-text content with Question Answering (QA) tasks. A general framework is to extract supporting evidence from the table and text and then perform numerical reasoning over extracted evidence for inferring the answer. However, existing models are vulnerable to missing supporting evidence, which limits their performance. In this work, we propose a novel Semantic-Oriented Hierarchical Graph (SoarGraph) that models the semantic relationships and dependencies among the different elements (e.g., question, table cells, text paragraphs, quantities, and dates) using hierarchical graphs to facilitate supporting evidence extraction and enhance numerical reasoning capability. We conduct our experiments on two popular benchmarks, FinQA and TAT-QA datasets, and the results show that our SoarGraph significantly outperforms all strong baselines, demonstrating remarkable effectiveness.
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1236-1244
Open AccessSoarGraph: Numerical Reasoning over Financial Table-Text Data via Semantic-Oriented Hierarchical Graphs
Towards the intelligent understanding of table-text data in the finance domain, previous research explores numerical reasoning over table-text content with Question Answering (QA) tasks. A general framework is to extract supporting evidence from the table and text and then perform numerical reasoning over extracted evidence for inferring the answer. However, existing models are vulnerable to missing supporting evidence, which limits their performance. In this work, we propose a novel Semantic-Oriented Hierarchical Graph (SoarGraph) that models the semantic relationships and dependencies among the different elements (e.g., question, table cells, text paragraphs, quantities, and dates) using hierarchical graphs to facilitate supporting evidence extraction and enhance numerical reasoning capability. We conduct our experiments on two popular benchmarks, FinQA and TAT-QA datasets, and the results show that our SoarGraph significantly outperforms all strong baselines, demonstrating remarkable effectiveness.
- 1 July 2020
- Published by Springer Nature in International Journal of Automotive Technology
- Vol. 21 (4) , 823-831
Control of DPPS in Vehicle Using Feed-Forward Decoupling
- 1 July 2020
- Published by Springer Nature in International Journal of Automotive Technology
- Vol. 21 (4) , 823-831
Control of DPPS in Vehicle Using Feed-Forward Decoupling
- Open Access
Explicit Utilization of General Knowledge in Machine Reading Comprehension
To bridge the gap between Machine Reading Comprehension (MRC) models and human beings, which is mainly reflected in the hunger for data and the robustness to noise, in this paper, we explore how to integrate the neural networks of MRC models with the general knowledge of human beings. On the one hand, we propose a data enrichment method, which uses WordNet to extract inter-word semantic connections as general knowledge from each given passage-question pair. On the other hand, we propose an end-to-end MRC model named as Knowledge Aided Reader (KAR), which explicitly uses the above extracted general knowledge to assist its attention mechanisms. Based on the data enrichment method, KAR is comparable in performance with the state-of-the-art MRC models, and significantly more robust to noise than them. When only a subset (20%-80%) of the training examples are available, KAR outperforms the state-of-the-art MRC models by a large margin, and is still reasonably robust to noise.
Open AccessExplicit Utilization of General Knowledge in Machine Reading Comprehension
To bridge the gap between Machine Reading Comprehension (MRC) models and human beings, which is mainly reflected in the hunger for data and the robustness to noise, in this paper, we explore how to integrate the neural networks of MRC models with the general knowledge of human beings. On the one hand, we propose a data enrichment method, which uses WordNet to extract inter-word semantic connections as general knowledge from each given passage-question pair. On the other hand, we propose an end-to-end MRC model named as Knowledge Aided Reader (KAR), which explicitly uses the above extracted general knowledge to assist its attention mechanisms. Based on the data enrichment method, KAR is comparable in performance with the state-of-the-art MRC models, and significantly more robust to noise than them. When only a subset (20%-80%) of the training examples are available, KAR outperforms the state-of-the-art MRC models by a large margin, and is still reasonably robust to noise.
- 1 January 2019
- Published by SCIK Publishing Corporation in Journal of Studies in Social Sciences
- Vol. 18 (2)
A Study on Promoting the Mechanism of the Rule of Thumb from the Perspective of the Smart Court in China
A Study on Promoting the Mechanism of the Rule of Thumb from the Perspective of the Smart Court in China
- 1 January 2019
- Published by SCIK Publishing Corporation in Journal of Studies in Social Sciences
- Vol. 18 (2)
A Study on Promoting the Mechanism of the Rule of Thumb from the Perspective of the Smart Court in China
A Study on Promoting the Mechanism of the Rule of Thumb from the Perspective of the Smart Court in China
- Open Access
- 1 May 2010
- Published by Elsevier in Expert Systems with Applications
- Vol. 37 (5) , 3737-3746
Collaborative management of web ontology data with flexible access control
- 1 May 2010
- Published by Elsevier in Expert Systems with Applications
- Vol. 37 (5) , 3737-3746
Open AccessCollaborative management of web ontology data with flexible access control