8 papers
Similarity-Aware Personalized Federated Learning in Heterogeneous Environments
Arun Kumar A, Sunil Gupta, Dang Ngyuen +2
Federated Learning (FL) allows decentralized clients to train models collaboratively while preserving data privacy. However, distribution mismatch across clients often leads to poo…
Uncertainty-Aware Budget Allocation for Adaptive Test-Time Reasoning
Manh Nguyen, Sunil Gupta, Hung Le
Sampling multiple responses improves language model reasoning, but uniform compute allocation is inefficient because easy questions are over-sampled while hard questions remain und…
Efficient Best-Of-N with Radial Consensus Score
Manh Nguyen, Sunil Gupta, Hung Le
Solving complex problems with large language models (LLMs) often requires selecting the best answer from multiple candidate responses (best-of-), yet identifying the most reliab…
Federated Domain Generalization with Latent Space Inversion
Ragja Palakkadavath, Hung Le, Thanh Nguyen-Tang +2
Federated domain generalization (FedDG) addresses distribution shifts among clients in a federated learning framework. FedDG methods aggregate the parameters of locally trained cli…
Distance Is All You Need: Radial Dispersion for Uncertainty Estimation in Large Language Models
Manh Nguyen, Sunil Gupta, Hung Le
Detecting uncertainty in large language models (LLMs) is essential for building reliable systems, yet many existing approaches are overly complex and depend on brittle semantic clu…
Probabilities Are All You Need: A Probability-Only Approach to Uncertainty Estimation in Large Language Models
Manh Nguyen, Sunil Gupta, Hung Le
Large Language Models (LLMs) exhibit strong performance across various natural language processing (NLP) tasks but remain vulnerable to hallucinations, generating factually incorre…
GRAD: Graph-Retrieved Adaptive Decoding for Hallucination Mitigation
Manh Nguyen, Sunil Gupta, Dai Do +1
Hallucination mitigation remains a persistent challenge for large language models (LLMs), even as model scales grow. Existing approaches often rely on external knowledge sources, s…
Retrieval-augmented Decoding for Improving Truthfulness in Open-ended Generation
Manh Nguyen, Sunil Gupta, Hung Le
Ensuring truthfulness in large language models (LLMs) remains a critical challenge for reliable text generation. While supervised fine-tuning and reinforcement learning with human…