Author name cluster

Xiangming Gu

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

2 author rows

ICLR Conference 2025 Conference Paper

On Calibration of LLM-based Guard Models for Reliable Content Moderation

Hongfu Liu 0002
Hengguan Huang
Xiangming Gu
Hao Wang 0014
Ye Wang 0007

Large language models (LLMs) pose significant risks due to the potential for generating harmful content or users attempting to evade guardrails. Existing studies have developed LLM-based guard models designed to moderate the input and output of threat LLMs, ensuring adherence to safety policies by blocking content that violates these protocols upon deployment. However, limited attention has been given to the reliability and calibration of such guard models. In this work, we empirically conduct comprehensive investigations of confidence calibration for 9 existing LLM-based guard models on 12 benchmarks in both user input and model output classification. Our findings reveal that current LLM-based guard models tend to 1) produce overconfident predictions, 2) exhibit significant miscalibration when subjected to jailbreak attacks, and 3) demonstrate limited robustness to the outputs generated by different types of response models. Additionally, we assess the effectiveness of post-hoc calibration methods to mitigate miscalibration. We demonstrate the efficacy of temperature scaling and, for the first time, highlight the benefits of contextual calibration for confidence calibration of guard models, particularly in the absence of validation sets. Our analysis and experiments underscore the limitations of current LLM-based guard models and provide valuable insights for the future development of well-calibrated guard models toward more reliable content moderation. We also advocate for incorporating reliability evaluation of confidence calibration when releasing future LLM-based guard models.

Details

TMLR Journal 2025 Journal Article

On Memorization in Diffusion Models

Xiangming Gu
Chao Du
Tianyu Pang
Chongxuan Li
Min Lin
Ye Wang

Due to their capacity to generate novel and high-quality samples, diffusion models have attracted significant research interest in recent years. Notably, the typical training objective of diffusion models, i.e., denoising score matching, has a closed-form optimal solution that can only generate training-data replicating samples. This indicates that a memorization behavior is theoretically expected, which contradicts the common generalization ability of state-of-the-art diffusion models, and thus calls for a deeper understanding. Looking into this, we first observe that memorization behaviors tend to occur on smaller-sized datasets, which motivates our definition of effective model memorization (EMM), a metric measuring the maximum size of training data at which a model approximates its theoretical optimum. Then, we quantify the impact of the influential factors on these memorization behaviors in terms of EMM, focusing primarily on data distribution, model configuration, and training procedure. Besides comprehensive empirical results identifying the influential factors, we surprisingly find that conditioning training data on uninformative random labels can significantly trigger the memorization in diffusion models. Our study holds practical significance for diffusion model users and offers clues to theoretical research in deep generative models.

PDF Details

NeurIPS Conference 2025 Conference Paper

SkyLadder: Better and Faster Pretraining via Context Window Scheduling

Tongyao Zhu
Qian Liu
Haonan Wang
Shiqi Chen
Xiangming Gu
Tianyu Pang
Min-Yen Kan

Recent advancements in LLM pretraining have featured ever-expanding context windows to process longer sequences. However, our controlled study reveals that models pretrained with shorter context windows consistently outperform their long-context counterparts under a fixed token budget. This finding motivates us to explore an optimal context window scheduling strategy to better balance long-context capability with pretraining efficiency. To this end, we propose SkyLadder, a simple yet effective approach that implements a short-to-long context window transition. SkyLadder preserves strong standard benchmark performance, while matching or exceeding baseline results on long-context tasks. Through extensive experiments, we pretrain 1B-parameter models (up to 32K context) and 3B-parameter models (8K context) on 100B tokens, demonstrating that SkyLadder yields consistent gains of up to 3. 7% on common benchmarks, while achieving up to 22% faster training speeds compared to baselines.

PDF Details

ICLR Conference 2025 Conference Paper

When Attention Sink Emerges in Language Models: An Empirical View

Xiangming Gu
Tianyu Pang
Chao Du
Qian Liu 0033
Fengzhuo Zhang
Cunxiao Du
Ye Wang 0007
Min Lin

Auto-regressive language Models (LMs) assign significant attention to the first token, even if it is not semantically important, which is known as **attention sink**. This phenomenon has been widely adopted in applications such as streaming/long context generation, KV cache optimization, inference acceleration, model quantization, and others. Despite its widespread use, a deep understanding of attention sink in LMs is still lacking. In this work, we first demonstrate that attention sinks exist universally in auto-regressive LMs with various inputs, even in small models. Furthermore, attention sink is observed to emerge during the LM pre-training, motivating us to investigate how *optimization*, *data distribution*, *loss function*, and *model architecture* in LM pre-training influence its emergence. We highlight that attention sink emerges after effective optimization on sufficient training data. The sink position is highly correlated with the loss function and data distribution. Most importantly, we find that attention sink acts more like key biases, *storing extra attention scores*, which could be non-informative and not contribute to the value computation. We also observe that this phenomenon (at least partially) stems from tokens' inner dependence on attention scores as a result of softmax normalization. After relaxing such dependence by replacing softmax attention with other attention operations, such as sigmoid attention without normalization, attention sinks do not emerge in LMs up to 1B parameters. The code is available at https://github.com/sail-sg/Attention-Sink.

Details

ICML Conference 2024 Conference Paper

Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

Xiangming Gu
Xiaosen Zheng
Tianyu Pang
Chao Du
Qian Liu 0033
Ye Wang 0007
Jing Jiang 0001
Min Lin

A multimodal large language model (MLLM) agent can receive instructions, capture images, retrieve histories from memory, and decide which tools to use. Nonetheless, red-teaming efforts have revealed that adversarial images/prompts can jailbreak an MLLM and cause unaligned behaviors. In this work, we report an even more severe safety issue in multi-agent environments, referred to as infectious jailbreak. It entails the adversary simply jailbreaking a single agent, and without any further intervention from the adversary, (almost) all agents will become infected exponentially fast and exhibit harmful behaviors. To validate the feasibility of infectious jailbreak, we simulate multi-agent environments containing up to one million LLaVA-1. 5 agents, and employ randomized pair-wise chat as a proof-of-concept instantiation for multi-agent interaction. Our results show that feeding an (infectious) adversarial image into the memory of any randomly chosen agent is sufficient to achieve infectious jailbreak. Finally, we derive a simple principle for determining whether a defense mechanism can provably restrain the spread of infectious jailbreak, but how to design a practical defense that meets this principle remains an open question to investigate.

Details

NeurIPS Conference 2022 Conference Paper

Extrapolative Continuous-time Bayesian Neural Network for Fast Training-free Test-time Adaptation

Hengguan Huang
Xiangming Gu
Hao Wang
Chang Xiao
Hongfu Liu
Ye Wang

Human intelligence has shown remarkably lower latency and higher precision than most AI systems when processing non-stationary streaming data in real-time. Numerous neuroscience studies suggest that such abilities may be driven by internal predictive modeling. In this paper, we explore the possibility of introducing such a mechanism in unsupervised domain adaptation (UDA) for handling non-stationary streaming data for real-time streaming applications. We propose to formulate internal predictive modeling as a continuous-time Bayesian filtering problem within a stochastic dynamical system context. Such a dynamical system describes the dynamics of model parameters of a UDA model evolving with non-stationary streaming data. Building on such a dynamical system, we then develop extrapolative continuous-time Bayesian neural networks (ECBNN), which generalize existing Bayesian neural networks to represent temporal dynamics and allow us to extrapolate the distribution of model parameters before observing the incoming data, therefore effectively reducing the latency. Remarkably, our empirical results show that ECBNN is capable of continuously generating better distributions of model parameters along the time axis given historical data only, thereby achieving (1) training-free test-time adaptation with low latency, (2) gradually improved alignment between the source and target features and (3) gradually improved model performance over time during the real-time testing stage.

PDF Details

TMLR Journal 2022 Journal Article

Unsupervised Mismatch Localization in Cross-Modal Sequential Data with Application to Mispronunciations Localization

Wei Wei
Hengguan Huang
Xiangming Gu
Hao Wang
Ye Wang

Content mismatch usually occurs when data from one modality is translated to another, e.g. language learners producing mispronunciations (errors in speech) when reading a sentence (target text) aloud. However, most existing alignment algorithms assume that the content involved in the two modalities is perfectly matched, thus leading to difficulty in locating such mismatch between speech and text. In this work, we develop an unsupervised learning algorithm that can infer the relationship between content-mismatched cross-modal sequential data, especially for speech-text sequences. More specifically, we propose a hierarchical Bayesian deep learning model, dubbed mismatch localization variational autoencoder (ML-VAE), which decomposes the generative process of the speech into hierarchically structured latent variables, indicating the relationship between the two modalities. Training such a model is very challenging due to the discrete latent variables with complex dependencies involved. To address this challenge, we propose a novel and effective training procedure that alternates between estimating the hard assignments of the discrete latent variables over a specifically designed mismatch localization finite-state acceptor (ML-FSA) and updating the parameters of neural networks. In this work, we focus on the mismatch localization problem for speech and text, and our experimental results show that ML-VAE successfully locates the mismatch between text and speech, without the need for human annotations for model training.

PDF Details