Hwee Tou Ng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Hwee Tou Ng has a total of 65 co-authors. Here are the top co-authors by number of shared publications:
- Muhammad Reza Qorib
Department of Computer Science National University of Singapore
10 shared publications - Hannan Cao
Department of Computer Science National University of Singapore
5 shared publications - Junyi Li
Department of Computer Science National University of Singapore
5 shared publications - Preslav Nakov
Mohamed bin Zayed University of Artificial Intelligence
4 shared publications - Tapas Nayak
Department of Computer Science National University of Singapore
3 shared publications - Alham Fikri Aji
Mohamed Zayed University of Artificial Intelligence Abu Dhabi UAE
2 shared publications
Latest Publications
- 15 September 2026
- Published by Springer Nature
- p. 41-59
GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents
- 15 September 2026
- Published by Springer Nature
- p. 41-59
GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents
- Open Access
The CoNLL-2013 Shared Task on Grammatical Error Correction
The CoNLL-2013 shared task was devoted to grammatical error correction. In this paper, we give the task definition, present the data sets, and describe the evaluation metric and scorer used in the shared task. We also give an overview of the various approaches adopted by the participating teams, and present the evaluation results.
Open AccessThe CoNLL-2013 Shared Task on Grammatical Error Correction
The CoNLL-2013 shared task was devoted to grammatical error correction. In this paper, we give the task definition, present the data sets, and describe the evaluation metric and scorer used in the shared task. We also give an overview of the various approaches adopted by the participating teams, and present the evaluation results.
- Open Access
Just Go Parallel: Improving the Multilingual Capabilities of Large Language Models
Large language models (LLMs) have demonstrated impressive translation capabilities even without being explicitly trained on parallel data. This remarkable property has led some to believe that parallel data is no longer necessary for building multilingual language models. While some attribute this to the emergent abilities of LLMs due to scale, recent work suggests that it is actually caused by incidental bilingual signals present in the training data. Various methods have been proposed to maximize the utility of parallel data to enhance the multilingual capabilities of multilingual encoder-based and encoder-decoder language models. However, some decoder-based LLMs opt to ignore parallel data instead. In this work, we conduct a systematic study on the impact of adding parallel data on LLMs' multilingual capabilities, focusing specifically on translation and multilingual common-sense reasoning. Through controlled experiments, we demonstrate that parallel data can significantly improve LLMs' multilingual capabilities.
Open AccessJust Go Parallel: Improving the Multilingual Capabilities of Large Language Models
Large language models (LLMs) have demonstrated impressive translation capabilities even without being explicitly trained on parallel data. This remarkable property has led some to believe that parallel data is no longer necessary for building multilingual language models. While some attribute this to the emergent abilities of LLMs due to scale, recent work suggests that it is actually caused by incidental bilingual signals present in the training data. Various methods have been proposed to maximize the utility of parallel data to enhance the multilingual capabilities of multilingual encoder-based and encoder-decoder language models. However, some decoder-based LLMs opt to ignore parallel data instead. In this work, we conduct a systematic study on the impact of adding parallel data on LLMs' multilingual capabilities, focusing specifically on translation and multilingual common-sense reasoning. Through controlled experiments, we demonstrate that parallel data can significantly improve LLMs' multilingual capabilities.
- Open Access
The Hallucination Dilemma: Factuality-Aware Reinforcement Learning for Large Reasoning Models
Large language models (LLMs) have significantly advanced in reasoning tasks through reinforcement learning (RL) optimization, achieving impressive capabilities across various challenging benchmarks. However, our empirical analysis reveals a critical drawback: reasoning-oriented RL fine-tuning significantly increases the prevalence of hallucinations. We theoretically analyze the RL training dynamics, identifying high-variance gradient, entropy-induced randomness, and susceptibility to spurious local optima as key factors leading to hallucinations. To address this drawback, we propose Factuality-aware Step-wise Policy Optimization (FSPO), an innovative RL fine-tuning algorithm incorporating explicit factuality verification at each reasoning step. FSPO leverages automated verification against given evidence to dynamically adjust token-level advantage values, incentivizing factual correctness throughout the reasoning process. Experiments across mathematical reasoning and hallucination benchmarks using Qwen2.5 and Llama models demonstrate that FSPO effectively reduces hallucinations while enhancing reasoning accuracy, substantially improving both reliability and performance.
Open AccessThe Hallucination Dilemma: Factuality-Aware Reinforcement Learning for Large Reasoning Models
Large language models (LLMs) have significantly advanced in reasoning tasks through reinforcement learning (RL) optimization, achieving impressive capabilities across various challenging benchmarks. However, our empirical analysis reveals a critical drawback: reasoning-oriented RL fine-tuning significantly increases the prevalence of hallucinations. We theoretically analyze the RL training dynamics, identifying high-variance gradient, entropy-induced randomness, and susceptibility to spurious local optima as key factors leading to hallucinations. To address this drawback, we propose Factuality-aware Step-wise Policy Optimization (FSPO), an innovative RL fine-tuning algorithm incorporating explicit factuality verification at each reasoning step. FSPO leverages automated verification against given evidence to dynamically adjust token-level advantage values, incentivizing factual correctness throughout the reasoning process. Experiments across mathematical reasoning and hallucination benchmarks using Qwen2.5 and Llama models demonstrate that FSPO effectively reduces hallucinations while enhancing reasoning accuracy, substantially improving both reliability and performance.
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (23) , 25065-25073
Just What You Desire: Constrained Timeline Summarization with Self-Reflection for Enhanced Relevance
Given news articles about an entity, such as a public figure or organization, timeline summarization (TLS) involves generating a timeline that summarizes the key events about the entity. However, the TLS task is too underspecified, since what is of interest to each reader may vary, and hence there is not a single ideal or optimal timeline. In this paper, we introduce a novel task, called Constrained Timeline Summarization (CTLS), where a timeline is generated in which all events in the timeline meet some constraint. An example of a constrained timeline concerns the legal battles of Tiger Woods, where only events related to his legal problems are selected to appear in the timeline. We collected a new human-verified dataset of constrained timelines involving 47 entities and 5 constraints per entity. We propose an approach that employs a large language model (LLM) to summarize news articles according to a specified constraint and cluster them to identify key events to include in a constrained timeline. In addition, we propose a novel self-reflection method during summary generation, demonstrating that this approach successfully leads to improved performance.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (23) , 25065-25073
Open AccessJust What You Desire: Constrained Timeline Summarization with Self-Reflection for Enhanced Relevance
Given news articles about an entity, such as a public figure or organization, timeline summarization (TLS) involves generating a timeline that summarizes the key events about the entity. However, the TLS task is too underspecified, since what is of interest to each reader may vary, and hence there is not a single ideal or optimal timeline. In this paper, we introduce a novel task, called Constrained Timeline Summarization (CTLS), where a timeline is generated in which all events in the timeline meet some constraint. An example of a constrained timeline concerns the legal battles of Tiger Woods, where only events related to his legal problems are selected to appear in the timeline. We collected a new human-verified dataset of constrained timelines involving 47 entities and 5 constraints per entity. We propose an approach that employs a large language model (LLM) to summarize news articles according to a specified constraint and cluster them to identify key events to include in a constrained timeline. In addition, we propose a novel self-reflection method during summary generation, demonstrating that this approach successfully leads to improved performance.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 26918-26936
DynaQuest: A Dynamic Question Answering Dataset Reflecting Real-World Knowledge Updates
Qian Lin, Junyi Li, Hwee Tou Ng. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 26918-26936
Open AccessDynaQuest: A Dynamic Question Answering Dataset Reflecting Real-World Knowledge Updates
Qian Lin, Junyi Li, Hwee Tou Ng. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 26859-26882
A Constrained Text Revision Agent via Iterative Planning and Searching
Hannan Cao, Hwee Tou Ng. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 26859-26882
Open AccessA Constrained Text Revision Agent via Iterative Planning and Searching
Hannan Cao, Hwee Tou Ng. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 9928-9942
Think&Cite: Improving Attributed Text Generation with Self-Guided Tree Search and Progress Reward Modeling
Junyi Li, Hwee Tou Ng. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 9928-9942
Open AccessThink&Cite: Improving Attributed Text Generation with Self-Guided Tree Search and Progress Reward Modeling
Junyi Li, Hwee Tou Ng. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 26967-26982
Rationalize and Align: Enhancing Writing Assistance with Rationale via Self-Training for Improved Alignment
Hannan Cao, Hai Ye, Hwee Tou Ng. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 26967-26982
Open AccessRationalize and Align: Enhancing Writing Assistance with Rationale via Self-Training for Improved Alignment
Hannan Cao, Hai Ye, Hwee Tou Ng. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 33411-33424
Just Go Parallel: Improving the Multilingual Capabilities of Large Language Models
Muhammad Reza Qorib, Junyi Li, Hwee Tou Ng. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 33411-33424
Open AccessJust Go Parallel: Improving the Multilingual Capabilities of Large Language Models
Muhammad Reza Qorib, Junyi Li, Hwee Tou Ng. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.