Author name cluster

Peiran Dong

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.

6 papers

2 author rows

ICLR Conference 2025 Conference Paper

Causally Motivated Sycophancy Mitigation for Large Language Models

Haoxi Li
Xueyang Tang
Jie Zhang 0076
Song Guo 0001
Sikai Bai
Peiran Dong
Yue Yu 0001

Incorporating user preferences into large language models (LLMs) can enhance the personalization and reliability of model outputs and facilitate the application of LLMs to real-world scenarios. However, leveraging user preferences can be a double-edged sword. Recent studies have found that improper utilization can incur sycophancy, where LLMs prioritize alignment with user preferences over the correctness of their outputs. To address sycophancy in LLMs, we analyze and model the problem through the lens of structured causal models (SCMs). We attribute sycophancy to LLMs' reliance on spurious correlations between user preferences and model outputs in this paper. Based on the proposed SCMs, we develop a novel framework, termed **CAUSM**, to mitigate sycophancy in LLMs by exploiting a significant causal signature. Specifically, we eliminate the spurious correlations embedded in the intermediate layers of LLMs through causally motivated head reweighting, and then calibrate the intra-head knowledge along the causal representation direction. Extensive experiments are conducted across diverse language tasks to demonstrate the superiority of our method over state-of-the-art competitors in mitigating sycophancy in LLMs.

Details

ICLR Conference 2025 Conference Paper

Durable Quantization Conditioned Misalignment Attack on Large Language Models

Peiran Dong
Haowei Li
Song Guo 0001

As large language models (LLMs) are increasingly deployed on resource-constrained edge devices, quantization techniques have been widely adopted to reduce model size and computational requirements. However, this process can expose models to new vulnerabilities. In this work, we introduce the Quantization Conditioned Misalignment (Q-Misalign) attack, a novel threat in which safety misalignment remains dormant in a full-precision LLM but becomes exploitable post-quantization. We demonstrate that our Q-Misalign attack effectively bypasses safety mechanisms and enables the generation of harmful content in quantized models while maintaining full-precision performance. Furthermore, we propose a contrastive task vector-based approach to enhance attack durability, ensuring that vulnerabilities persist even after downstream fine-tuning. Experimental results show that Q-Misalign attack significantly increases jailbreak success rates in quantized models, while preserving model utility and safety alignment in full precision. Our findings highlight a critical gap in current LLM safety measures and call for more robust defenses in quantization-aware scenarios.

Details

ICML Conference 2024 Conference Paper

Easing Concept Bleeding in Diffusion via Entity Localization and Anchoring

Jiewei Zhang
Song Guo 0001
Peiran Dong
Jie Zhang 0076
Ziming Liu
Yue Yu 0001
Xiaoming Wu

Recent diffusion models have manifested extraordinary capabilities in generating high-quality, diverse, and innovative images guided by textual prompts. Nevertheless, these state-of-the-art models may encounter the challenge of concept bleeding when generating images with multiple entities or attributes in the prompt, leading to the unanticipated merging or overlapping of distinct objects in the synthesized result. The current work exploits auxiliary networks to produce mask-constrained regions for entities, necessitating the training of an object detection network. In this paper, we investigate the bleeding reason and find that the cross-attention map associated with a specific entity or attribute tends to extend beyond its intended focus, encompassing the background or other unrelated objects and thereby acting as the primary source of concept bleeding. Motivated by this, we propose Entity Localization and Anchoring (ELA) to drive the entity to concentrate on the expected region accurately during inference, eliminating the necessity for training. Specifically, we initially identify the region corresponding to each entity and subsequently employ a tailored loss function to anchor entities within their designated positioning areas. Extensive experiments demonstrate its superior capability in precisely generating multiple objects as specified in the textual prompts.

Details

NeurIPS Conference 2024 Conference Paper

Towards Safe Concept Transfer of Multi-Modal Diffusion via Causal Representation Editing

Peiran Dong
Bingjie Wang
Song Guo
Junxiao Wang
Jie Zhang
Zicong Hong

Recent advancements in vision-language-to-image (VL2I) diffusion generation have made significant progress. While generating images from broad vision-language inputs holds promise, it also raises concerns about potential misuse, such as copying artistic styles without permission, which could have legal and social consequences. Therefore, it's crucial to establish governance frameworks to ensure ethical and copyright integrity, especially with widely used diffusion models. To address these issues, researchers have explored various approaches, such as dataset filtering, adversarial perturbations, machine unlearning, and inference-time refusals. However, these methods often lack either scalability or effectiveness. In response, we propose a new framework called causal representation editing (CRE), which extends representation editing from large language models (LLMs) to diffusion-based models. CRE enhances the efficiency and flexibility of safe content generation by intervening at diffusion timesteps causally linked to unsafe concepts. This allows for precise removal of harmful content while preserving acceptable content quality, demonstrating superior effectiveness, precision and scalability compared to existing methods. CRE can handle complex scenarios, including incomplete or blurred representations of unsafe concepts, offering a promising solution to challenges in managing harmful content generation in diffusion-based models.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Towards Test-Time Refusals via Concept Negation

Peiran Dong
Song Guo
Junxiao Wang
Bingjie Wang
Jiewei Zhang
Ziming Liu

Generative models produce unbounded outputs, necessitating the use of refusal techniques to confine their output space. Employing generative refusals is crucial in upholding the ethical and copyright integrity of synthesized content, particularly when working with widely adopted diffusion models. "Concept negation'' presents a promising paradigm to achieve generative refusals, as it effectively defines and governs the model's output space based on concepts, utilizing natural language interfaces that are readily comprehensible to humans. However, despite the valuable contributions of prior research to the field of concept negation, it still suffers from significant limitations. The existing concept negation methods, which operate based on the composition of score or noise predictions from the diffusion process, are limited to independent concepts (e. g. , ``a blonde girl`` without ``glasses``) and fail to consider the interconnected nature of concepts in reality (e. g. , ``Mickey mouse eats ice cream`` without ``Disney characters``). Keeping the limitations in mind, we propose a novel framework, called $ProtoRe$, to improve the flexibility of concept negation via test-time negative concept identification along with purification in the feature space. $ProtoRe$ works by incorporating CLIP's language-contrastive knowledge to identify the prototype of negative concepts, extract the negative features from outputs using the prototype as a prompt, and further refine the attention maps by retrieving negative features. Our evaluation on multiple benchmarks shows that $ProtoRe$ outperforms state-of-the-art methods under various settings, in terms of the effectiveness of purification and the fidelity of generative images.

PDF Details

TIST Journal 2019 Journal Article

Deep Reinforcement Learning for Vehicular Edge Computing

Zhaolong Ning
Peiran Dong
Xiaojie Wang
Joel J. P. C. Rodrigues
Feng Xia

The development of smart vehicles brings drivers and passengers a comfortable and safe environment. Various emerging applications are promising to enrich users’ traveling experiences and daily life. However, how to execute computing-intensive applications on resource-constrained vehicles still faces huge challenges. In this article, we construct an intelligent offloading system for vehicular edge computing by leveraging deep reinforcement learning. First, both the communication and computation states are modelled by finite Markov chains. Moreover, the task scheduling and resource allocation strategy is formulated as a joint optimization problem to maximize users’ Quality of Experience (QoE). Due to its complexity, the original problem is further divided into two sub-optimization problems. A two-sided matching scheme and a deep reinforcement learning approach are developed to schedule offloading requests and allocate network resources, respectively. Performance evaluations illustrate the effectiveness and superiority of our constructed system.

Details DOI