4 citations · 6 across the 8 of their papers we have counts for
10 papers
Copying Is Not Grounding: Training Faithful Long-Form RAG with Authored-Sentence Credit
Hoang Pham, Duc Anh Vu, Duy Tung Doan +2
In search engines and assistants, long-form RAG answers can mislead readers with claims their sources do not support. Faithfulness rewards, the share of supported sentences, train…
Reinforcing Step-level Reasoning for Effective Self-Correction in LLMs
Vu Duc Anh, Nhat M. Hoang, Do Xuan Long +3
Achieving effective self-correction, where models verify and correct their own mistakes, remains a fundamental challenge for large language models (LLMs). In this work, we propose…
From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models
Ponhvoan Srey, Xiaobao Wu, Cong-Duy Nguyen +3
Probe-based uncertainty estimation (UE) has emerged as a prominent approach to detect hallucinations in Large Language Models (LLMs) by learning uncertainty from internal model sig…
More Bias, Less Bias: BiasPrompting for Enhanced Multiple-Choice Question Answering
Duc Anh Vu, Thong Nguyen, Cong-Duy Nguyen +2
With the advancement of large language models (LLMs), their performance on multiple-choice question (MCQ) tasks has improved significantly. However, existing approaches face key li…
CutPaste&Find: Efficient Multimodal Hallucination Detector with Visual-aid Knowledge Base
Cong-Duy Nguyen, Xiaobao Wu, Duc Anh Vu +3
Large Vision-Language Models (LVLMs) have demonstrated impressive multimodal reasoning capabilities, but they remain susceptible to hallucination, particularly object hallucination…
Curriculum Demonstration Selection for In-Context Learning
Duc Anh Vu, Nguyen Tran Cong Duy, Xiaobao Wu +4
Large Language Models (LLMs) have shown strong in-context learning (ICL) abilities with a few demonstrations. However, one critical challenge is how to select demonstrations to eli…
ToXCL: A Unified Framework for Toxic Speech Detection and Explanation
Nhat M. Hoang, Xuan Long Do, Duc Anh Do +2
The proliferation of online toxic speech is a pertinent problem posing threats to demographic groups. While explicit toxic speech contains offensive lexical signals, implicit one c…
Improving Multimodal Sentiment Analysis: Supervised Angular Margin-based Contrastive Learning for Enhanced Fusion Representation
Cong-Duy Nguyen, Thong Nguyen, Duc Anh Vu +1
The effectiveness of a model is heavily reliant on the quality of the fusion representation of multiple modalities in multimodal sentiment analysis. Moreover, each modality is extr…
ChatGPT as a Math Questioner? Evaluating ChatGPT on Generating Pre-university Math Questions
Phuoc Pham Van Long, Duc Anh Vu, Nhat M. Hoang +2
Mathematical questioning is crucial for assessing students problem-solving skills. Since manually creating such questions requires substantial effort, automatic methods have been e…
Building Footprint Extraction in Dense Areas using Super Resolution and Frame Field Learning
Vuong Nguyen, Anh Ho, Duc-Anh Vu +2
Despite notable results on standard aerial datasets, current state-of-the-arts fail to produce accurate building footprints in dense areas due to challenging properties posed by th…