Weijie Zhao

Author directory

2026

With the widespread adoption of Large Language Models (LLMs), concerns about potential misuse have emerged. To this end, watermarking has been adapted to LLM, enabling a simple and effective way to detect and monitor generated text. However, while the existing methods can differentiate between watermarked and unwatermarked text with high accuracy, they often face a trade-off between the quality of the generated text and the effectiveness of the watermarking process. In this work, we present a novel type of LLM watermark, Sparse WatermARK (or SpARK), which aims to mitigate this trade-off by applying watermarks to a small subset of generated tokens distributed across the text. To demonstrate this type of watermark, we introduce two novel variants, SpARK-P and SpARK-R, which achieve sparsity by anchoring watermarked tokens to words that have specific Part-of-Speech (POS) tags and specific hash values w.r.t a pseudorandom hash function, respectively. Our experimental results demonstrate that the proposed watermarking schemes, albeit embarrassingly simple, are incredibly effective, achieving high detectability while generating text that outperforms previous LLM watermarking methods in quality across various tasks. SpARK further advances the watermarking capability for LLMs while maintaining their generated text quality.
Large Language Models (LLMs) are vulnerable to attacks like prompt injection, backdoor attacks, and adversarial attacks, which manipulate prompts or models to generate harmful outputs. In this paper, departing from traditional deep learning attack paradigms, we explore their intrinsic relationship and collectively term them Prompt Trigger Attacks (PTA). This raises a key question: Given a prompt, can we tell whether a hidden trigger is steering the model’s behavior? To address this, we propose UniGuardian, the first unified, training-free defense that detects trigger-activated prompt injection, backdoor, and adversarial attacks by measuring how structured perturbations of the prompt shift the model’s output distribution. Additionally, we introduce a single-forward strategy to optimize the detection pipeline, enabling simultaneous attack detection and text generation within a single forward pass. Our experiments confirm that UniGuardian accurately and efficiently identifies trigger-activated prompts in LLMs.
Autoregressive (AR) models have recently shown strong performance in image generation, where a key component is the visual tokenizer (VT) that maps continuous pixels into discrete tokens. The quality of the VT largely determines the upper bound of AR model performance. However, existing discrete VTs significantly lag behind continuous variational autoencoders (VAEs), leading to degraded reconstructions and poor preservation of fine details and text. Current benchmarks primarily evaluate end-to-end generation quality, making it difficult to isolate VT performance. We introduce VTBench, a comprehensive benchmark for systematic evaluation of visual tokenizers across three core tasks: image reconstruction, detail preservation, and text preservation. Evaluating state-of-the-art VTs with multiple metrics, we find that continuous VAEs consistently outperform discrete VTs, especially in retaining spatial structure and semantic details. Discrete VTs often produce distorted reconstructions and fail to preserve fine textures and text. We release VTBench publicly to facilitate future research on robust, general-purpose visual tokenizers.

2025

Large Language Models (LLMs) have revolutionized natural language processing, but their widespread use has raised significant copyright concerns. This tutorial addresses the complex intersection of LLMs and copyright law, providing researchers and practitioners with essential knowledge and tools to navigate this challenging landscape. The tutorial begins with an overview of relevant copyright principles and their application to AI, followed by an examination of specific copyright issues in LLM development and deployment. A key focus will be on technical approaches to copyright risk assessment and mitigation in LLMs. We will introduce benchmarks for evaluating copyright-related risks, including memorization detection and probing techniques. The tutorial will then cover practical mitigation strategies, such as machine unlearning, efficient fine-tuning methods, and alignment approaches to reduce copyright infringement risks. Ethical considerations and future directions in copyright-aware AI development will also be discussed.
Large Language Models (LLMs) heavily rely on high-quality training data, making data valuation crucial for optimizing model performance, especially when working within a limited budget. In this work, we aim to offer a third-party data valuation approach that benefits both data providers and model developers. We introduce a linearized future influence kernel (LinFiK), which assesses the value of individual data samples in improving LLM performance during training. We further propose ALinFiK, a learning strategy to approximate LinFiK, enabling scalable data valuation. Our comprehensive evaluations demonstrate that this approach surpasses existing baselines in effectiveness and efficiency, demonstrating significant scalability advantages as LLM parameters increase.

2024

Given a Large Language Model (LLM) generation, how can we identify which training data led to this generation? In this paper, we proposed RapidIn, a scalable framework adapting to LLMs for estimating the influence of each training data. The proposed framework consists of two stages: caching and retrieval. First, we compress the gradient vectors by over 200,000x, allowing them to be cached on disk or in GPU/CPU memory. Then, given a generation, RapidIn efficiently traverses the cached gradients to estimate the influence within minutes, achieving over a 6,326x speedup. Moreover, RapidIn supports multi-GPU parallelization to substantially accelerate caching and retrieval. Our empirical result confirms the efficiency and effectiveness of RapidIn.