23 citations · 38 across the 31 of their papers we have counts for
35 papers
UniGuard: Multi-View Guardrail Learning for Cross-Interface Safety Generalization
Viet-Thanh Pham, Thuy-Trang Vu, Junae Kim +4
Guardrail models are increasingly used as safety layers for LLMs and agentic systems, but most are trained on fixed prompt or response interfaces and become unreliable when the sam…
Anticipating Social Consequences with Distributional World Models
Viet-Thanh Pham, Thuy-Trang Vu, Zhuang Li +2
Social world models predict how interactions develop after an action, helping agents negotiate, cooperate and mediate. In these situations, one action can lead to several plausible…
A Responsibility-Centered Coordination Mechanism for Decentralized Multi-Agent Systems
Thi-Nhung Nguyen, Viet-Thanh Pham, Linhao Luo +2
Centralized orchestration provides comprehensive multi-agent coordination but creates bottlenecks in scalability, adaptability, and collective performance. Decentralized approaches…
E-Orch: Towards Effective, Efficient, and Extensible Agentic Orchestration with Reinforcement Learning
Junnan Liu, Linhao Luo, Thuy-Trang Vu +1
Agentic orchestration enables multiple autonomous agents to solve complex tasks through adaptive decomposition, delegation, and execution. However, existing orchestrators often rel…
AIPO: Learning to Reason from Active Interaction
Junnan Liu, Linhao Luo, Thuy-Trang Vu +1
Recent advances in LLMs have demonstrated strong reasoning capabilities, largely stimulated by RLVR. However, the exploration of existing RLVR algorithms remains largely constraine…
GTS: Inference-Time Scaling of Latent Reasoning with a Learnable Gaussian Thought Sampler
Minghan Wang, Ye Bai, Thuy-Trang Vu +2
Inference-time scaling (ITS) in latent reasoning models typically relies on heuristic perturbations, such as dropout or fixed Gaussian noise, to generate diverse candidate trajecto…
LiveCultureBench: a Multi-Agent, Multi-Cultural Benchmark for Large Language Models in Dynamic Social Simulations
Viet-Thanh Pham, Lizhen Qu, Thuy-Trang Vu +2
Large language models (LLMs) are increasingly deployed as autonomous agents, yet evaluations focus primarily on task success rather than cultural appropriateness or evaluator relia…
Discourse Graph Guided Document Translation with Large Language Models
Viet-Thanh Pham, Minghan Wang, Hao-Han Liao +1
Adapting large language models to full document translation remains challenging due to the difficulty of capturing long-range dependencies and preserving discourse coherence throug…
Towards Inference-time Scaling for Continuous Space Reasoning
Minghan Wang, Thuy-Trang Vu, Ehsan Shareghi +1
Inference-time scaling through multiple sample generation in combination with Process- or Outcome-Reward Model (PRM or ORM) re-ranking has proven effective for text-based reasoning…
Beyond Imitation: Recovering Dense Rewards from Demonstrations
Jiangnan Li, Thuy-Trang Vu, Ehsan Abbasnejad +1
Conventionally, supervised fine-tuning (SFT) is treated as a simple imitation learning process that only trains a policy to imitate expert behavior on demonstration datasets. In th…
The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems
Thi-Nhung Nguyen, Linhao Luo, Amardeep Kaur +5
Bias in large language models (LLMs) remains a persistent challenge, often leading to stereotyping and unfair treatment across social groups. While prior work has mainly focused on…
G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge
Linhao Luo, Zicheng Zhao, Junnan Liu +9
Large language models (LLMs) excel at complex reasoning but remain limited by static and incomplete parametric knowledge. Retrieval-augmented generation (RAG) mitigates this by inc…
Improving Table Understanding with LLMs and Entity-Oriented Search
Thi-Nhung Nguyen, Hoang Ngo, Dinh Phung +2
Our work addresses the challenges of understanding tables. Existing methods often struggle with the unpredictable nature of table content, leading to a reliance on preprocessing an…
Planning for Success: Exploring LLM Long-term Planning Capabilities in Table Understanding
Thi-Nhung Nguyen, Hoang Ngo, Dinh Phung +2
Table understanding is key to addressing challenging downstream tasks such as table-based question answering and fact verification. Recent works have focused on leveraging Chain-of…
Discrete Minds in a Continuous World: Do Language Models Know Time Passes?
Minghan Wang, Ye Bai, Thuy-Trang Vu +2
While Large Language Models (LLMs) excel at temporal reasoning tasks like event ordering and duration estimation, their ability to perceive the actual passage of time remains unexp…
MAPLE: Multi-Agent Adaptive Planning with Long-Term Memory for Table Reasoning
Ye Bai, Minghan Wang, Thuy-Trang Vu
Table-based question answering requires complex reasoning capabilities that current LLMs struggle to achieve with single-pass inference. Existing approaches, such as Chain-of-Thoug…
SituatedThinker: Grounding LLM Reasoning with Real-World through Situated Thinking
Junnan Liu, Linhao Luo, Thuy-Trang Vu +1
Recent advances in large language models (LLMs) demonstrate their impressive reasoning capabilities. However, the reasoning confined to internal parametric space limits LLMs' acces…
SpeechDialogueFactory: Generating High-Quality Speech Dialogue Data to Accelerate Your Speech-LLM Development
Minghan Wang, Ye Bai, Yuxia Wang +3
High-quality speech dialogue datasets are crucial for Speech-LLM development, yet existing acquisition methods face significant limitations. Human recordings incur high costs and p…
CONGRAD:Conflicting Gradient Filtering for Multilingual Preference Alignment
Jiangnan Li, Thuy-Trang Vu, Christian Herold +3
Naive joint training of large language models (LLMs) for multilingual preference alignment can suffer from negative interference. This is a known issue in multilingual training, wh…
Proverbs Run in Pairs: Evaluating Proverb Translation Capability of Large Language Model
Minghan Wang, Viet-Thanh Pham, Farhad Moghimifar +1
Despite achieving remarkable performance, machine translation (MT) research remains underexplored in terms of translating cultural elements in languages, such as idioms, proverbs,…
Extending LLMs to New Languages: A Case Study of Llama and Persian Adaptation
Samin Mahdizadeh Sani, Pouya Sadeghi, Thuy-Trang Vu +2
Large language models (LLMs) have made great progress in classification and text generation tasks. However, they are mainly trained on English data and often struggle with low-reso…
SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Models
Zhuang Li, Yuncheng Hua, Thuy-Trang Vu +3
Recent studies emphasize that manually ensuring a consistent response style and maintaining high data quality in training sets can significantly improve the performance of fine-tun…
Exploring the Potential of Multimodal LLM with Knowledge-Intensive Multimodal ASR
Minghan Wang, Yuxia Wang, Thuy-Trang Vu +2
Recent advancements in multimodal large language models (MLLMs) have made significant progress in integrating information across various modalities, yet real-world applications in…
Mixture-of-Skills: Learning to Optimize Data Usage for Fine-Tuning Large Language Models
Minghao Wu, Thuy-Trang Vu, Lizhen Qu +1
Large language models (LLMs) are typically fine-tuned on diverse and extensive datasets sourced from various origins to develop a comprehensive range of skills, such as writing, re…