85 citations · 126 across the 13 of their papers we have counts for
13 papers
Native Multilingual Chain-of-Thought Reasoning in Low-Resource Southeast Asian Languages
Sean Gip Lim, William Chandra Tjhi, Hai Leong Chieu
Large Language Models have achieved substantial progress in reasoning capabilities. Yet in low-resource native settings, many suffer from cross-lingual collapse, reverting to Engli…
Tokenizer-Agnostic Engram Module
Jia Peng Lim, Hai Leong Chieu
Deepseek's Engram, a conditional memory module, was introduced to trade-off storage versus reasoning in large language models. However, the module relies on token-level -gram ha…
Spokes: Optimizing for Diverse Pretraining Data Selection
Clarence Lee, Yejin Choi, Luke Zettlemoyer +2
Diversity plays a critical role in data selection, improving performance under fixed data budgets by reducing redundancy and repetition. However, optimizing for diversity is inhere…
Lessons from Training Grounded LLMs with Verifiable Rewards
Shang Hong Sim, Tej Deep Pala, Vernon Toh +5
Generating grounded and trustworthy responses remains a key challenge for large language models (LLMs). While retrieval-augmented generation (RAG) with citation-based grounding hol…
Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse
Maojia Song, Shang Hong Sim, Rishabh Bhardwaj +3
LLMs are an integral component of retrieval-augmented generation (RAG) systems. While many studies focus on evaluating the overall quality of end-to-end RAG systems, there is a gap…
Multi-label and Multi-target Sampling of Machine Annotation for Computational Stance Detection
Zhengyuan Liu, Hai Leong Chieu, Nancy F. Chen
Data collection from manual labeling provides domain-specific and task-aligned supervision for data-driven approaches, and a critical mass of well-annotated resources is required t…
Guiding Computational Stance Detection with Expanded Stance Triangle Framework
Zhengyuan Liu, Yong Keong Yap, Hai Leong Chieu +1
Stance detection determines whether the author of a piece of text is in favor of, against, or neutral towards a specified target, and can be used to gain valuable insights into soc…
Interpretable Rumor Detection in Microblogs by Attending to User Interactions
Ling Min Serena Khoo, Hai Leong Chieu, Zhong Qian +1
We address rumor detection by learning to differentiate between the community's response to real and fake claims in microblogs. Existing state-of-the-art models are based on tree m…
Chemical Structure Elucidation from Mass Spectrometry by Matching Substructures
Jing Lim, Joshua Wong, Minn Xuan Wong +4
Chemical structure elucidation is a serious bottleneck in analytical chemistry today. We address the problem of identifying an unknown chemical threat given its mass spectrum and i…
Universal Dependencies Parsing for Colloquial Singaporean English
Hongmin Wang, Yue Zhang, GuangYong Leonard Chan +2
Singlish can be interesting to the ACL community both linguistically as a major creole based on English, and computationally for information extraction and sentiment analysis of re…
Relaxed Survey Propagation for The Weighted Maximum Satisfiability Problem
Hai Leong Chieu, Wee Sun Sun Lee
The survey propagation (SP) algorithm has been shown to work well on large instances of the random 3-SAT problem near its phase transition. It was shown that SP estimates marginals…
Optimizing F-measure: A Tale of Two Approaches
Ye Nan, Kian Ming Chai, Wee Sun Lee +1
F-measures are popular performance metrics, particularly for tasks with imbalanced data sets. Algorithms for learning to maximize F-measures follow two approaches: the empirical ut…
A Split-Merge Framework for Comparing Clusterings
Qiaoliang Xiang, Qi Mao, Kian Ming Chai +3
Clustering evaluation measures are frequently used to evaluate the performance of algorithms. However, most measures are not properly normalized and ignore some information in the…