Author name cluster

Hai Le

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

1 author row

AAAI Conference 2026 Short Paper

Unveiling AI Safety in Fine-tuning Quantized Model

Hai Le

Post-training quantization is widely used to compress large language models (LLMs) for efficient deployment in resource-constrained environments. However, recent work shows that quantization, especially aggressive schemes such as 4-bit QLoRA, can substantially degrade safety alignment, making models more vulnerable to harmful completions and jailbreaks. In this work, we investigate these safety risks and propose a mitigation strategy: projecting quantized parameters back into safety-aligned subspaces. First, we empirically measure safety degradation on benchmark datasets using both safety and utility metrics. Next, we explore projection-based restoration methods to recover alignment-preserving directions in the LoRA adapters of quantized models. Finally, we study how quantization affects mechanistic safety neurons and how hybrid-precision designs can preserve them. By foregrounding the safety implications of model compression, this work aims to support more robust, deployment-ready, and ethically aligned LLMs.

PDF Details DOI

PRL Workshop 2020 Workshop Paper

Safe Learning of Lifted Action Models

Brendan Juba
Hai Le
Roni Stern

Creating a domain model, even for classical, domainindependent planning, is a notoriously hard knowledgeengineering task. A natural approach to solve this problem is to use learning, but learning approaches frequently do not provide guarantees of safety: variously, actions may fail or may not lead to the desired outcome. In some domains such failures are not acceptable, due to the cost of failure or inability to replan online after failure. In such settings, all learning must be done offline, based on some observations collected, e. g. , by some other agents or a human. Through this learning, the task is to generate a plan that is guaranteed to be successful. This is called the model-free planning problem. Prior work proposed an algorithm for solving the model-free planning problem in classical planning. However, they were limited to learning grounded domains, and thus they could not scale. We generalize this prior work and propose the first safe model-free planning algorithm for lifted domains. We prove the correctness of our approach, and provide a statistical analysis showing that the number of trajectories needed to solve future problems with high probability is linear in the potential size of the domain model. We also present experiments demonstrating that our approach scales favorably in practice.

PDF Details