4 citations · 5 across the 5 of their papers we have counts for
4 papers · 1 filter
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…
A Comparative Analysis of Contextual Representation Flow in State-Space and Transformer Architectures
Nhat M. Hoang, Do Xuan Long, Cong-Duy Nguyen +2
State Space Models (SSMs) have recently emerged as efficient alternatives to Transformer-Based Models (TBMs) for long-sequence processing with linear scaling, yet how contextual in…
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…
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…