From the 1 of 7 linked papers with an AI index.
7 papers
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…
TIGER: Text-Conditioned Visual Gated Routing with Acceptance Alignment for Multimodal Speculative Decoding
Quynh Vo, Cong-Duy Nguyen, Ponhvoan Srey +2
The paper introduces TIGER, a framework that speeds up multimodal generation by dynamically selecting only the visual tokens relevant to the current textual context and training th…
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…
Learning Uncertainty from Sequential Internal Dispersion in Large Language Models
Ponhvoan Srey, Xiaobao Wu, Cong-Duy Nguyen +1
Uncertainty estimation is a promising approach to detect hallucinations in large language models (LLMs). Recent approaches commonly depend on model internal states to estimate unce…
Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models
Ponhvoan Srey, Quang Minh Nguyen, Xiaobao Wu +1
Uncertainty estimation (UE) aims to detect hallucinated outputs of large language models (LLMs) to improve their reliability. However, UE metrics often exhibit unstable performance…
Uncover and Unlearn Nuisances: Agnostic Fully Test-Time Adaptation
Ponhvoan Srey, Yaxin Shi, Hangwei Qian +2
Fully Test-Time Adaptation (FTTA) addresses domain shifts without access to source data and training protocols of the pre-trained models. Traditional strategies that align source a…