papers

Publications (38)

cs.LG2024

LISA: Learning-Integrated Space Partitioning Framework for Traffic Accident Forecasting on Heterogeneous Spatiotemporal Data

Bang An, Xun Zhou, Amin Vahedian +3

Traffic accident forecasting is an important task for intelligent transportation management and emergency response systems. However, this problem is challenging due to the spatial…

cs.LG2025

AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security

Zikui Cai, Shayan Shabihi, Bang An +5

We introduce AegisLLM, a cooperative multi-agent defense against adversarial attacks and information leakage. In AegisLLM, a structured workflow of autonomous agents - orchestrator…

cs.LG2025

Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?

Michael-Andrei Panaitescu-Liess, Zora Che, Bang An +6

Large Language Models (LLMs) have demonstrated impressive capabilities in generating diverse and contextually rich text. However, concerns regarding copyright infringement arise as…

cs.CR2023

AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models

Sicheng Zhu, Ruiyi Zhang, Bang An +6

Safety alignment of Large Language Models (LLMs) can be compromised with manual jailbreak attacks and (automatic) adversarial attacks. Recent studies suggest that defending against…

cs.LG2025

Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence

Yibo Yang, Sihao Liu, Chuan Rao +5

Conventional low-rank adaptation methods build adapters without considering data context, leading to sub-optimal fine-tuning performance and severe forgetting of inherent world kno…

cs.CL2025

GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment

Yuancheng Xu, Udari Madhushani Sehwag, Alec Koppel +4

Large Language Models (LLMs) exhibit impressive capabilities but require careful alignment with human preferences. Traditional training-time methods finetune LLMs using human prefe…

cs.AI2025

Purifying Task Vectors in Knowledge-Aware Subspace for Model Merging

Bang An, Yibo Yang, Philip Torr +1

Model merging aims to integrate task-specific abilities from individually fine-tuned models into a single model without extra training. In recent model merging methods, task vector…

cs.LG2024

Referee-Meta-Learning for Fast Adaptation of Locational Fairness

Weiye Chen, Yiqun Xie, Xiaowei Jia +4

When dealing with data from distinct locations, machine learning algorithms tend to demonstrate an implicit preference of some locations over the others, which constitutes biases t…

cs.LG2025

PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models

Michael-Andrei Panaitescu-Liess, Pankayaraj Pathmanathan, Yigitcan Kaya +5

As the capabilities of large language models (LLMs) continue to expand, their usage has become increasingly prevalent. However, as reflected in numerous ongoing lawsuits regarding…

cs.LG2026

HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models

Aznaur Aliev, Carlos Hinojosa, Abdelrahman Eldesokey +3

HyperSafe introduces a post‑hoc, model‑specific safe side network generated by a hypernetwork that classifies prompts using activation fingerprints, allowing fine‑tuned language mo…

#language model safety#fine-tuning#hypernetwork#prompt classification
cs.LG2023

Understanding the Generalization Benefit of Model Invariance from a Data Perspective

Sicheng Zhu, Bang An, Furong Huang

Machine learning models that are developed with invariance to certain types of data transformations have demonstrated superior generalization performance in practice. However, the…

cs.CL2025

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models

Bang An, Shiyue Zhang, Mark Dredze

Efforts to ensure the safety of large language models (LLMs) include safety fine-tuning, evaluation, and red teaming. However, despite the widespread use of the Retrieval-Augmented…

cs.CV2024

WAVES: Benchmarking the Robustness of Image Watermarks

Bang An, Mucong Ding, Tahseen Rabbani +8

In the burgeoning age of generative AI, watermarks act as identifiers of provenance and artificial content. We present WAVES (Watermark Analysis Via Enhanced Stress-testing), a ben…

cs.CL2024

AceGPT, Localizing Large Language Models in Arabic

Huang Huang, Fei Yu, Jianqing Zhu +17

This paper is devoted to the development of a localized Large Language Model (LLM) specifically for Arabic, a language imbued with unique cultural characteristics inadequately addr…

cs.LG2020

Repulsive Attention: Rethinking Multi-head Attention as Bayesian Inference

Bang An, Jie Lyu, Zhenyi Wang +6

The neural attention mechanism plays an important role in many natural language processing applications. In particular, the use of multi-head attention extends single-head attentio…

cs.CL2024

Ensuring Safety and Trust: Analyzing the Risks of Large Language Models in Medicine

Yifan Yang, Qiao Jin, Robert Leaman +15

The remarkable capabilities of Large Language Models (LLMs) make them increasingly compelling for adoption in real-world healthcare applications. However, the risks associated with…

cs.LG2023

Transferring Fairness under Distribution Shifts via Fair Consistency Regularization

Bang An, Zora Che, Mucong Ding +1

The increasing reliance on ML models in high-stakes tasks has raised a major concern on fairness violations. Although there has been a surge of work that improves algorithmic fairn…

cs.LG2021

Adaptive Transfer Learning on Graph Neural Networks

Xueting Han, Zhenhuan Huang, Bang An +1

Graph neural networks (GNNs) is widely used to learn a powerful representation of graph-structured data. Recent work demonstrates that transferring knowledge from self-supervised t…

cs.CL2020

Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints

Zhenyi Wang, Xiaoyang Wang, Bang An +2

Text generation from a knowledge base aims to translate knowledge triples to natural language descriptions. Most existing methods ignore the faithfulness between a generated text d…

cs.CL2023

On the Possibilities of AI-Generated Text Detection

Souradip Chakraborty, Amrit Singh Bedi, Sicheng Zhu +3

Our work addresses the critical issue of distinguishing text generated by Large Language Models (LLMs) from human-produced text, a task essential for numerous applications. Despite…

cs.LG2024

SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation

Mucong Ding, Bang An, Yuancheng Xu +2

Data augmentation, a cornerstone technique in deep learning, is crucial in enhancing model performance, especially with scarce labeled data. While traditional techniques are effect…

cs.LG2025

EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles

Aakriti Agrawal, Mucong Ding, Zora Che +6

With Large Language Models (LLMs) rapidly approaching and potentially surpassing human-level performance, it has become imperative to develop approaches capable of effectively supe…

cs.CR2026

Defending Against Harmful Supervision Hidden in Benign Samples

Bang An, Yibo Yang, Dandan Guo +3

Existing defenses are effective when harmful content is explicitly mixed into downstream fine-tuning data, but crafted samples can instead hide harmful supervision inside benign ta…

cs.CL2024

Explore Spurious Correlations at the Concept Level in Language Models for Text Classification

Yuhang Zhou, Paiheng Xu, Xiaoyu Liu +3

Language models (LMs) have achieved notable success in numerous NLP tasks, employing both fine-tuning and in-context learning (ICL) methods. While language models demonstrate excep…

physics.optics2025

Uniform and Tunable Structural Colors based on Ultrathin Lignin Optical Coatings

Bang An, Anran Mao, Torbjorn Pettersson +4

Structural coloration offers a sustainable and non-fading alternative to conventional pigment- and dye-based colorants. In this study, we present a scalable strategy for generating…

cs.LG2023

SpatialRank: Urban Event Ranking with NDCG Optimization on Spatiotemporal Data

Bang An, Xun Zhou, Yongjian Zhong +1

The problem of urban event ranking aims at predicting the top-k most risky locations of future events such as traffic accidents and crimes. This problem is of fundamental importanc…

cs.LG2020

Guess First to Enable Better Compression and Adversarial Robustness

Sicheng Zhu, Bang An, Shiyu Niu

Machine learning models are generally vulnerable to adversarial examples, which is in contrast to the robustness of humans. In this paper, we try to leverage one of the mechanisms…

cs.CL2025

Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion

Jianqing Zhu, Huang Huang, Zhihang Lin +18

This paper addresses the critical need for democratizing large language models (LLM) in the Arab world, a region that has seen slower progress in developing models comparable to st…

cs.CL2024

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs

Juhao Liang, Zhenyang Cai, Jianqing Zhu +9

The alignment of large language models (LLMs) is critical for developing effective and safe language models. Traditional approaches focus on aligning models during the instruction…

cs.AI2023

Talking Models: Distill Pre-trained Knowledge to Downstream Models via Interactive Communication

Zhe Zhao, Qingyun Liu, Huan Gui +3

Many recent breakthroughs in machine learning have been enabled by the pre-trained foundation models. By scaling up model parameters, training data, and computation resources, foun…

cs.LG2023

C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder

Xiaoyu Liu, Jiaxin Yuan, Bang An +3

Representation learning assumes that real-world data is generated by a few semantically meaningful generative factors (i.e., sources of variation) and aims to discover them in the…

cs.LG2024

GeoPro-Net: Learning Interpretable Spatiotemporal Prediction Models through Statistically-Guided Geo-Prototyping

Bang An, Xun Zhou, Zirui Zhou +3

The problem of forecasting spatiotemporal events such as crimes and accidents is crucial to public safety and city management. Besides accuracy, interpretability is also a key requ…

cs.LG2022

HintNet: Hierarchical Knowledge Transfer Networks for Traffic Accident Forecasting on Heterogeneous Spatio-Temporal Data

Bang An, Amin Vahedian, Xun Zhou +2

Traffic accident forecasting is a significant problem for transportation management and public safety. However, this problem is challenging due to the spatial heterogeneity of the…

cs.CL2025

Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models

Bang An, Sicheng Zhu, Ruiyi Zhang +3

Safety-aligned large language models (LLMs) sometimes falsely refuse pseudo-harmful prompts, like "how to kill a mosquito," which are actually harmless. Frequent false refusals not…

cs.CV2024

PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts

Bang An, Sicheng Zhu, Michael-Andrei Panaitescu-Liess +2

Vision-language models like CLIP are widely used in zero-shot image classification due to their ability to understand various visual concepts and natural language descriptions. How…

cs.LG2025

GFairHint: Improving Individual Fairness for Graph Neural Networks via Fairness Hint

Paiheng Xu, Yuhang Zhou, Bang An +2

Given the growing concerns about fairness in machine learning and the impressive performance of Graph Neural Networks (GNNs) on graph data learning, algorithmic fairness in GNNs ha…

cs.LG2024

Sketch-GNN: Scalable Graph Neural Networks with Sublinear Training Complexity

Mucong Ding, Tahseen Rabbani, Bang An +2

Graph Neural Networks (GNNs) are widely applied to graph learning problems such as node classification. When scaling up the underlying graphs of GNNs to a larger size, we are force…

cs.LG2025

EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles

Aakriti Agrawal, Mucong Ding, Zora Che +6

With Large Language Models (LLMs) rapidly approaching and potentially surpassing human-level performance, it has become imperative to develop approaches capable of effectively supe…