Search Results for author:
Found 29 papers, 16 papers with code
AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security
On the WMDP unlearning benchmark, AegisLLM achieves near-perfect unlearning with only 20 training examples and fewer than 300 LM calls.
PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models
In this paper, we introduce PoisonedParrot: the first stealthy data poisoning attack that induces an LLM to generate copyrighted content even when the model has not been directly trained on the specific copyrighted material.
LISA: Learning-Integrated Space Partitioning Framework for Traffic Accident Forecasting on Heterogeneous Spatiotemporal Data
Traffic accident forecasting is an important task for intelligent transportation management and emergency response systems.
GeoPro-Net: Learning Interpretable Spatiotemporal Prediction Models through Statistically-Guided Geo-Prototyping
Interpretation of the spatiotemporal forecasting mechanism is, however, challenging due to the complexity of multi-source spatiotemporal features, the non-intuitive nature of spatiotemporal patterns for non-expert users, and the presence of spatial heterogeneity in the data.
Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion
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 state-of-the-art offerings like GPT-4 or ChatGPT 3. 5, due to a predominant focus on mainstream languages (e. g., English and Chinese).
Alignment at Pre-training! Towards Native Alignment for Arabic LLMs
The alignment of large language models (LLMs) is critical for developing effective and safe language models.
Ensuring Safety and Trust: Analyzing the Risks of Large Language Models in Medicine
The remarkable capabilities of Large Language Models (LLMs) make them increasingly compelling for adoption in real-world healthcare applications.
GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment
Traditional training-time methods finetune LLMs using human preference datasets but incur significant training costs and require repeated training to handle diverse user preferences.
SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation
Data augmentation, a cornerstone technique in deep learning, is crucial in enhancing model performance, especially with scarce labeled data.
Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models
Our method and dataset can help developers evaluate and fine-tune safer and more usable LLMs.
Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
Surprisingly, we find that watermarking adversely affects the success rate of MIAs, complicating the task of detecting copyrighted text in the pretraining dataset.
Sketch-GNN: Scalable Graph Neural Networks with Sublinear Training Complexity
Graph Neural Networks (GNNs) are widely applied to graph learning problems such as node classification.
Referee-Meta-Learning for Fast Adaptation of Locational Fairness
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 that sabotage the spatial fairness of the algorithm.
WAVES: Benchmarking the Robustness of Image Watermarks
Our evaluation examines two pivotal dimensions: the degree of image quality degradation and the efficacy of watermark detection after attacks.
Explore Spurious Correlations at the Concept Level in Language Models for Text Classification
We find that LMs, when encountering spurious correlations between a concept and a label in training or prompts, resort to shortcuts for predictions.
C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder
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 latent space.
AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models
Safety alignment of Large Language Models (LLMs) can be compromised with manual jailbreak attacks and (automatic) adversarial attacks.
Talking Models: Distill Pre-trained Knowledge to Downstream Models via Interactive Communication
In this paper, we extend KD with an interactive communication process to help students of downstream tasks learn effectively from pre-trained foundation models.
AceGPT, Localizing Large Language Models in Arabic
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 addressed by current mainstream models.
PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts
Inspired by it, we observe that providing CLIP with contextual attributes improves zero-shot image classification and mitigates reliance on spurious features.
GFairHint: Improving Individual Fairness for Graph Neural Networks via Fairness Hint
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 has attracted significant attention.
On the Possibilities of AI-Generated Text Detection
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.
Transferring Fairness under Distribution Shifts via Fair Consistency Regularization
In many real-world applications, however, such an assumption is often violated as previously trained fair models are often deployed in a different environment, and the fairness of such models has been observed to collapse.
HintNet: Hierarchical Knowledge Transfer Networks for Traffic Accident Forecasting on Heterogeneous Spatio-Temporal Data
However, this problem is challenging due to the spatial heterogeneity of the environment and the sparsity of accidents in space and time.
Understanding the Generalization Benefit of Model Invariance from a Data Perspective
Based on this notion, we refine the generalization bound for invariant models and characterize the suitability of a set of data transformations by the sample covering number induced by transformations, i. e., the smallest size of its induced sample covers.
Adaptive Transfer Learning on Graph Neural Networks
We design an adaptive auxiliary loss weighting model to learn the weights of auxiliary tasks by quantifying the consistency between auxiliary tasks and the target task.
Repulsive Attention: Rethinking Multi-head Attention as Bayesian Inference
The neural attention mechanism plays an important role in many natural language processing applications.
Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints
Text generation from a knowledge base aims to translate knowledge triples to natural language descriptions.
Guess First to Enable Better Compression and Adversarial Robustness
Machine learning models are generally vulnerable to adversarial examples, which is in contrast to the robustness of humans.
