Author name cluster

Hui Liu 0031

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.

7 papers

1 author row

ICLR Conference 2025 Conference Paper

Catastrophic Failure of LLM Unlearning via Quantization

Zhiwei Zhang 0028
Fali Wang
Xiaomin Li
Zongyu Wu 0001
Xianfeng Tang
Hui Liu 0031
Qi He 0002
Wenpeng Yin 0001

Large language models (LLMs) have shown remarkable proficiency in generating text, benefiting from extensive training on vast textual corpora. However, LLMs may also acquire unwanted behaviors from the diverse and sensitive nature of their training data, which can include copyrighted and private content. Machine unlearning has been introduced as a viable solution to remove the influence of such problematic content without the need for costly and time-consuming retraining. This process aims to erase specific knowledge from LLMs while preserving as much model utility as possible. Despite the effectiveness of current unlearning methods, little attention has been given to whether existing unlearning methods for LLMs truly achieve forgetting or merely hide the knowledge, which current unlearning benchmarks fail to detect. This paper reveals that applying quantization to models that have undergone unlearning can restore the "forgotten" information. We conduct comprehensive experiments using various quantization techniques across multiple precision levels to thoroughly evaluate this phenomenon. We find that for unlearning methods with utility constraints, the unlearned model retains an average of 21\% of the intended forgotten knowledge in full precision, which significantly increases to 83\% after 4-bit quantization. Based on our empirical findings, we provide a theoretical explanation for the observed phenomenon and propose a quantization-robust unlearning strategy aimed at mitigating this intricate issue. Our results highlight a fundamental tension between preserving the utility of the unlearned model and preventing knowledge recovery through quantization, emphasizing the challenge of balancing these two objectives. Altogether, our study underscores a major failure in existing unlearning methods for LLMs, strongly advocating for more comprehensive and robust strategies to ensure authentic unlearning without compromising model utility. Our code is available at: https://github.com/zzwjames/FailureLLMUnlearning.

Details

ICML Conference 2025 Conference Paper

Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing

Tianci Liu 0003
Ruirui Li 0002
Zihan Dong
Hui Liu 0031
Xianfeng Tang
Qingyu Yin
Linjun Zhang
Haoyu Wang 0004

Large language models (LLMs) have achieved remarkable performance on various natural language tasks. However, they are trained on static corpora and their knowledge can become outdated quickly in the fast-changing world. This motivates the development of knowledge editing (KE) to update specific knowledge in LLMs without changing unrelated others or compromising their pre-trained capabilities. Previous efforts sought to update a small amount of parameters of a LLM and proved effective for making selective updates. Nonetheless, the edited LLM often exhibits degraded ability to reason about the new knowledge. In this work, we identify a key issue: heterogeneous token overfitting (HTO), where the LLM overfits different tokens in the provided knowledge at varying rates. To tackle this, we propose OVERTONE, a token-level smoothing method that mitigates HTO by adaptively refining the target distribution. Theoretically, OVERTONE offers better parameter updates with negligible computation overhead. It also induces an implicit DPO but does not require preference data pairs. Extensive experiments across four editing methods, two LLMs, and diverse scenarios demonstrate the effectiveness and versatility of our method.

Details

ICLR Conference 2025 Conference Paper

Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning

Tianci Liu 0003
Ruirui Li 0002
Yunzhe Qi
Hui Liu 0031
Xianfeng Tang
Tianqi Zheng
Qingyu Yin
Monica Xiao Cheng

Large language models (LLMs) have achieved remarkable performance on vari- ous natural language tasks. However, they are trained on static corpora and their knowledge can become outdated quickly in the fast-changing world. This moti- vates the development of knowledge editing methods designed to update certain knowledge in LLMs without changing unrelated others. To make selective edits, previous efforts often sought to update a small amount of parameters in some spe- cific layer(s) of a LLM. Nonetheless, in challenging scenarios, they still fall short in making successful edits while preserving knowledge irrelevant to the updates simultaneously, resulting in a notable editing-locality trade-off. In this work, we question if the trade-offs are caused by the fact that parameter-based updates have a global effect, i.e., edited parameters affect all inputs indiscriminately. In light of this, we explore the feasibility of representation fine-tuning, which applied some linear update to a few representations in a learned subspace, for knowledge edit- ing. While being effective to enhance an LLM’s general ability as demonstrated in the previous work, we theoretically show that this linear update imposes a tension in editing-locality trade-off. Subsequently, BaFT is proposed to break the linear- ity. BaFT computes a weight for each basis that spans a dimension of the subspace based on the input representation. This input-dependent weighting mechanism al- lows BaFT to manage different types of knowledge in an adaptive way, thereby achieving a better editing-locality trade-off. Experiments on three LLMs with five editing benchmarks in diverse scenarios show the superiority of our method.

Details

ICLR Conference 2024 Conference Paper

Label-free Node Classification on Graphs with Large Language Models (LLMs)

Zhikai Chen
Haitao Mao
Hongzhi Wen
Haoyu Han 0001
Wei Jin 0009
Haiyang Zhang
Hui Liu 0031
Jiliang Tang

In recent years, there have been remarkable advancements in node classification achieved by Graph Neural Networks (GNNs). However, they necessitate abundant high-quality labels to ensure promising performance. In contrast, Large Language Models (LLMs) exhibit impressive zero-shot proficiency on text-attributed graphs. Yet, they face challenges in efficiently processing structural data and suffer from high inference costs. In light of these observations, this work introduces a label-free node classification on graphs with LLMs pipeline, LLM-GNN. It amalgamates the strengths of both GNNs and LLMs while mitigating their limitations. Specifically, LLMs are leveraged to annotate a small portion of nodes and then GNNs are trained on LLMs' annotations to make predictions for the remaining large portion of nodes. The implementation of LLM-GNN faces a unique challenge: how can we actively select nodes for LLMs to annotate and consequently enhance the GNN training? How can we leverage LLMs to obtain annotations of high quality, representativeness, and diversity, thereby enhancing GNN performance with less cost? To tackle this challenge, we develop an annotation quality heuristic and leverage the confidence scores derived from LLMs to advanced node selection. Comprehensive experimental results validate the effectiveness of LLM-GNN. In particular, LLM-GNN can achieve an accuracy of 74.9\% on a vast-scale dataset \products with a cost less than 1 dollar.

Details

ICLR Conference 2024 Conference Paper

Sharpness-Aware Data Poisoning Attack

Pengfei He
Han Xu 0002
Jie Ren 0019
Yingqian Cui
Shenglai Zeng
Hui Liu 0031
Charu C. Aggarwal
Jiliang Tang

Recent research has highlighted the vulnerability of Deep Neural Networks (DNNs) against data poisoning attacks. These attacks aim to inject poisoning samples into the models' training dataset such that the trained models have inference failures. While previous studies have executed different types of attacks, one major challenge that greatly limits their effectiveness is the uncertainty of the re-training process after the injection of poisoning samples. It includes the uncertainty of training initialization, algorithm and model architecture. To address this challenge, we propose a new strategy called **Sharpness-Aware Data Poisoning Attack (SAPA)**. In particular, it leverages the concept of DNNs' loss landscape sharpness to optimize the poisoning effect on the (approximately) worst re-trained model. Extensive experiments demonstrate that SAPA offers a general and principled strategy that significantly enhances various types of poisoning attacks against various types of re-training uncertainty.

Details

ICLR Conference 2024 Conference Paper

Structural Fairness-aware Active Learning for Graph Neural Networks

Haoyu Han 0001
Xiaorui Liu
Li Ma 0012
MohamadAli Torkamani
Hui Liu 0031
Jiliang Tang
Makoto Yamada

Graph Neural Networks (GNNs) have seen significant achievements in semi-supervised node classification. Yet, their efficacy often hinges on access to high-quality labeled node samples, which may not always be available in real-world scenarios. While active learning is commonly employed across various domains to pinpoint and label high-quality samples based on data features, graph data present unique challenges due to their intrinsic structures that render nodes non-i.i.d. Furthermore, biases emerge from the positioning of labeled nodes; for instance, nodes closer to the labeled counterparts often yield better performance. To better leverage graph structure and mitigate structural bias in active learning, we present a unified optimization framework (SCARCE), which is also easily incorporated with node features. Extensive experiments demonstrate that the proposed method not only improves the GNNs performance but also paves the way for more fair results.

Details

ICML Conference 2023 Conference Paper

Probabilistic Categorical Adversarial Attack and Adversarial Training

Han Xu 0002
Pengfei He
Jie Ren 0019
Yuxuan Wan
Zitao Liu 0001
Hui Liu 0031
Jiliang Tang

The studies on adversarial attacks and defenses have greatly improved the robustness of Deep Neural Networks (DNNs). Most advanced approaches have been overwhelmingly designed for continuous data such as images. However, these achievements are still hard to be generalized to categorical data. To bridge this gap, we propose a novel framework, Probabilistic Categorical Adversarial Attack (or PCAA). It transfers the discrete optimization problem of finding categorical adversarial examples to a continuous problem that can be solved via gradient-based methods. We analyze the optimality (attack success rate) and time complexity of PCAA to demonstrate its significant advantage over current search-based attacks. More importantly, through extensive empirical studies, we demonstrate that the well-established defenses for continuous data, such as adversarial training and TRADES, can be easily accommodated to defend DNNs for categorical data.

Details