43 citations · 83 across the 40 of their papers we have counts for
41 papers
Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs
Jingtan Wang, Arun Verma, Xiaoqiang Lin +4
How to divide a fixed annotation budget between supervised fine-tuning (SFT) and reinforcement learning (RL) during LLM post-training remains an open problem. Existing work charact…
CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia
Bryan Chen Zhengyu Tan, Weihua Zheng, Thong T. Doan +30
Current cultural evaluations for large language models (LLMs) often reduce culture to single-turn factual recall via MCQs, failing to capture a common use case: users seeking pract…
SagaQA: A Multi-hop Reasoning Benchmark for Long-form Narrative Understanding in TV Series
Galann Pennec, Zhengyuan Liu, Nicholas Asher +2
We introduce SagaQA, a long-form video benchmark for multi-hop reasoning over full-length TV series. Existing video reasoning benchmarks often emphasize local understanding of adja…
ARBOR: Online Process Rewards via a Reusable Rubric Buffer for Search Agents
Zheng Liu, Longxiang Zhang, Xintong Wang +8
LLM-based search agents are trained predominantly with outcome-only reward, leaving the search process itself unsupervised. This signal degenerates on outcome-homogeneous groups wh…
How Hard Can It Be? Hardness-Aware Multi-Objective Unlearning
Jiangwei Chen, Xinyuan Niu, Rachael Hwee Ling Sim +3
Machine unlearning aims to remove the influence of specific forget training data due to privacy, copyright or bias concerns while maintaining the model performance on the remaining…
SemEval-2026 Task 7: Everyday Knowledge Across Diverse Languages and Cultures
Nedjma Ousidhoum, Junho Myung, Carla Perez-Almendros +27
We present our shared task on evaluating the adaptability of LLMs and NLP systems across multiple languages and cultures. The task data consist of an extended version of our manual…
Rethinking Bayesian Optimization for Co-Optimizing LLM Training Configurations
Zhiliang Chen, Alfred Wei Lun Leong, Shao Yong Ong +6
Fine-tuning an LLM to maximize performance on a downstream task requires finding the optimal data and model configuration. This is a black-box optimization problem that Bayesian op…
Minimal Clips, Maximum Salience: Long Video Summarization via Key Moment Extraction
Galann Pennec, Zhengyuan Liu, Nicholas Asher +2
Vision-Language Models (VLMs) are able to process increasingly longer videos. Yet, important visual information is easily lost throughout the entire context and missed by VLMs. Als…
Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD
Bryan Chen Zhengyu Tan, Daniel Wai Kit Chin, Zhengyuan Liu +2
Large Language Models (LLMs) can struggle to balance gullibility to misinformation and resistance to valid corrections in persuasive dialogues, a critical challenge for reliable de…
COGENT: A Curriculum-oriented Framework for Generating Grade-appropriate Educational Content
Zhengyuan Liu, Stella Xin Yin, Dion Hoe-Lian Goh +1
While Generative AI has demonstrated strong potential and versatility in content generation, its application to educational contexts presents several challenges. Models often fail…
SingaKids: A Multilingual Multimodal Dialogic Tutor for Language Learning
Zhengyuan Liu, Geyu Lin, Hui Li Tan +8
The integration of generative artificial intelligence into educational applications has enhanced personalized and interactive learning experiences, and it shows strong potential to…
Integrating Video and Text: A Balanced Approach to Multimodal Summary Generation and Evaluation
Galann Pennec, Zhengyuan Liu, Nicholas Asher +2
Vision-Language Models (VLMs) often struggle to balance visual and textual information when summarizing complex multimodal inputs, such as entire TV show episodes. In this paper, w…
MERaLiON-TextLLM: Cross-Lingual Understanding of Large Language Models in Chinese, Indonesian, Malay, and Singlish
Xin Huang, Tarun Kumar Vangani, Minh Duc Pham +4
Multilingual large language models (MLLMs) have shown impressive capabilities across a variety of languages. However, efficacy can differ greatly between different language familie…
AudioBench: A Universal Benchmark for Audio Large Language Models
Bin Wang, Xunlong Zou, Geyu Lin +6
We introduce AudioBench, a universal benchmark designed to evaluate Audio Large Language Models (AudioLLMs). It encompasses 8 distinct tasks and 26 datasets, among which, 7 are new…
CRAFT: Extracting and Tuning Cultural Instructions from the Wild
Bin Wang, Geyu Lin, Zhengyuan Liu +2
Large language models (LLMs) have rapidly evolved as the foundation of various natural language processing (NLP) applications. Despite their wide use cases, their understanding of…
Scaffolding Language Learning via Multi-modal Tutoring Systems with Pedagogical Instructions
Zhengyuan Liu, Stella Xin Yin, Carolyn Lee +1
Intelligent tutoring systems (ITSs) that imitate human tutors and aim to provide immediate and customized instructions or feedback to learners have shown their effectiveness in edu…
CrossIn: An Efficient Instruction Tuning Approach for Cross-Lingual Knowledge Alignment
Geyu Lin, Bin Wang, Zhengyuan Liu +1
Multilingual proficiency presents a significant challenge for large language models (LLMs). English-centric models are usually suboptimal in other languages, particularly those tha…
Resilience of Large Language Models for Noisy Instructions
Bin Wang, Chengwei Wei, Zhengyuan Liu +2
As the rapidly advancing domain of natural language processing (NLP), large language models (LLMs) have emerged as powerful tools for interpreting human commands and generating tex…
Personality-aware Student Simulation for Conversational Intelligent Tutoring Systems
Zhengyuan Liu, Stella Xin Yin, Geyu Lin +1
Intelligent Tutoring Systems (ITSs) can provide personalized and self-paced learning experience. The emergence of large language models (LLMs) further enables better human-machine…
Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing
Fangkai Jiao, Chengwei Qin, Zhengyuan Liu +2
Large Language Models (LLMs) have demonstrated significant potential in handling complex reasoning tasks through step-by-step rationale generation. However, recent studies have rai…
Picking the Underused Heads: A Network Pruning Perspective of Attention Head Selection for Fusing Dialogue Coreference Information
Zhengyuan Liu, Nancy F. Chen
The Transformer-based models with the multi-head self-attention mechanism are widely used in natural language processing, and provide state-of-the-art results. While the pre-traine…
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…
CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation
Minzhi Li, Taiwei Shi, Caleb Ziems +4
Annotated data plays a critical role in Natural Language Processing (NLP) in training models and evaluating their performance. Given recent developments in Large Language Models (L…
Instructive Dialogue Summarization with Query Aggregations
Bin Wang, Zhengyuan Liu, Nancy F. Chen
Conventional dialogue summarization methods directly generate summaries and do not consider user's specific interests. This poses challenges in cases where the users are more focus…