Moxin Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Moxin Li has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Fuli Feng
National University of Singapore, Singapore, Singapore
4 shared publications - Tat-Seng Chua
National University of Singapore, Singapore, Singapore
3 shared publications - Chao Wang
ESTATES PTE LTD, Singapore, Singapore
2 shared publications - Fengbin Zhu
National University of Singapore, Singapore, Singapore
2 shared publications - Wenjie Wang
National University of Singapore, Singapore, Singapore
2 shared publications - Chongming Gao
University of Science and Technology of China, Hefei, Anhui, China
1 shared publication
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13455-13456
PILA'26: Personal Intelligence in Agentic AI Era
Large language models (LLMs) and agentic AI systems are rapidly moving into user-facing applications, yet most remain fundamentally generic, optimized for population-level objectives under the assumption that one model can serve all users. This assumption is increasingly misaligned with real-world deployment, where AI systems interact continuously with individuals whose preferences, knowledge, goals, and values evolve over time. PILA'26 is motivated by the need to move beyond static general models toward personal intelligence ---AI systems that explicitly model users and dynamically adapt their reasoning, behavior, and decisions through memory, interaction, and lifelong learning. The workshop brings together researchers and practitioners from data mining, LLMs, NLP, IR, human-centered AI, and AI safety to position personalization as a central research direction for next-generation AI systems at KDD. Topics include user memory and personalized alignment, self-evolving and lifelong learning, datasets and evaluation, real-world applications, and trustworthiness in user-adaptive AI. Workshop website: https://pila26-workshop.github.io.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13455-13456
Open AccessPILA'26: Personal Intelligence in Agentic AI Era
Large language models (LLMs) and agentic AI systems are rapidly moving into user-facing applications, yet most remain fundamentally generic, optimized for population-level objectives under the assumption that one model can serve all users. This assumption is increasingly misaligned with real-world deployment, where AI systems interact continuously with individuals whose preferences, knowledge, goals, and values evolve over time. PILA'26 is motivated by the need to move beyond static general models toward personal intelligence ---AI systems that explicitly model users and dynamically adapt their reasoning, behavior, and decisions through memory, interaction, and lifelong learning. The workshop brings together researchers and practitioners from data mining, LLMs, NLP, IR, human-centered AI, and AI safety to position personalization as a central research direction for next-generation AI systems at KDD. Topics include user memory and personalized alignment, self-evolving and lifelong learning, datasets and evaluation, real-world applications, and trustworthiness in user-adaptive AI. Workshop website: https://pila26-workshop.github.io.
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4086-4089
Unveiling Knowledge Boundary of Large Language Models for Trustworthy Information Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4086-4089
Open AccessUnveiling Knowledge Boundary of Large Language Models for Trustworthy Information Access
- 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.
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 1220-1236
Hypothetical Training for Robust Machine Reading Comprehension of Tabular Context
Moxin Li, Wenjie Wang, Fuli Feng, Hanwang Zhang, Qifan Wang, Tat-Seng Chua. Findings of the Association for Computational Linguistics: ACL 2023. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 1220-1236
Open AccessHypothetical Training for Robust Machine Reading Comprehension of Tabular Context
Moxin Li, Wenjie Wang, Fuli Feng, Hanwang Zhang, Qifan Wang, Tat-Seng Chua. Findings of the Association for Computational Linguistics: ACL 2023. 2023.