16 citations · 73 across the 29 of their papers we have counts for
30 papers
EGiME: Entropy-Guided Model Evaluation in Few-Shot Learning
Dequan Jin, Tao Li, Lifeng Xing +2
The feature-extraction quality of pre-trained models sets the ceiling of downstream transfer learning, yet few-shot model selection remains difficult: supervised evaluation on scar…
Why Do Large Language Models Generate Harmful Content?
Rajesh Ganguli, Raha Moraffah
Large Language Models (LLMs) have been shown to generate harmful content. However, the underlying causes of such behavior remain under explored. We propose a causal mediation analy…
DAGverse: Building Document-Grounded Semantic DAGs from Scientific Papers
Shu Wan, Saketh Vishnubhatla, Iskander Kushbay +4
Directed Acyclic Graphs (DAGs) are widely used to represent structured knowledge in scientific and technical domains. However, datasets for real-world DAGs remain scarce because co…
Active Domain Knowledge Acquisition with 100-Dollar Budget: Enhancing LLMs via Cost-Efficient, Expert-Involved Interaction in Sensitive Domains
Yang Wu, Raha Moraffah, Rujing Yao +3
Large Language Models (LLMs) have demonstrated an impressive level of general knowledge. However, they often struggle in highly specialized and cost-sensitive domains such as drug…
Can Large Language Models Infer Causal Relationships from Real-World Text?
Ryan Saklad, Aman Chadha, Oleg Pavlov +1
Understanding and inferring causal relationships from texts is a core aspect of human cognition and is essential for advancing large language models (LLMs) towards artificial gener…
"Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models
Zhen Tan, Chengshuai Zhao, Raha Moraffah +5
Retrieval-Augmented Generative (RAG) models enhance Large Language Models (LLMs) by integrating external knowledge bases, improving their performance in applications like fact-chec…
Navigating the Shadows: Unveiling Effective Disturbances for Modern AI Content Detectors
Ying Zhou, Ben He, Le Sun
With the launch of ChatGPT, large language models (LLMs) have attracted global attention. In the realm of article writing, LLMs have witnessed extensive utilization, giving rise to…
Zero-shot LLM-guided Counterfactual Generation: A Case Study on NLP Model Evaluation
Amrita Bhattacharjee, Raha Moraffah, Joshua Garland +1
With the development and proliferation of large, complex, black-box models for solving many natural language processing (NLP) tasks, there is also an increasing necessity of method…
Cross-Platform Hate Speech Detection with Weakly Supervised Causal Disentanglement
Paras Sheth, Tharindu Kumarage, Raha Moraffah +2
Content moderation faces a challenging task as social media's ability to spread hate speech contrasts with its role in promoting global connectivity. With rapidly evolving slang an…
EAGLE: A Domain Generalization Framework for AI-generated Text Detection
Amrita Bhattacharjee, Raha Moraffah, Joshua Garland +1
With the advancement in capabilities of Large Language Models (LLMs), one major step in the responsible and safe use of such LLMs is to be able to detect text generated by these mo…
A Survey of AI-generated Text Forensic Systems: Detection, Attribution, and Characterization
Tharindu Kumarage, Garima Agrawal, Paras Sheth +4
We have witnessed lately a rapid proliferation of advanced Large Language Models (LLMs) capable of generating high-quality text. While these LLMs have revolutionized text generatio…
Exploiting Class Probabilities for Black-box Sentence-level Attacks
Raha Moraffah, Huan Liu
Sentence-level attacks craft adversarial sentences that are synonymous with correctly-classified sentences but are misclassified by the text classifiers. Under the black-box settin…
Adversarial Text Purification: A Large Language Model Approach for Defense
Raha Moraffah, Shubh Khandelwal, Amrita Bhattacharjee +1
Adversarial purification is a defense mechanism for safeguarding classifiers against adversarial attacks without knowing the type of attacks or training of the classifier. These te…
A Generative Approach to Surrogate-based Black-box Attacks
Raha Moraffah, Huan Liu
Surrogate-based black-box attacks have exposed the heightened vulnerability of DNNs. These attacks are designed to craft adversarial examples for any samples with black-box target…
Causal Feature Selection for Responsible Machine Learning
Raha Moraffah, Paras Sheth, Saketh Vishnubhatla +1
Machine Learning (ML) has become an integral aspect of many real-world applications. As a result, the need for responsible machine learning has emerged, focusing on aligning ML mod…
The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative
Zhen Tan, Chengshuai Zhao, Raha Moraffah +4
Due to their unprecedented ability to process and respond to various types of data, Multimodal Large Language Models (MLLMs) are constantly defining the new boundary of Artificial…
VQA-GEN: A Visual Question Answering Benchmark for Domain Generalization
Suraj Jyothi Unni, Raha Moraffah, Huan Liu
Visual question answering (VQA) models are designed to demonstrate visual-textual reasoning capabilities. However, their real-world applicability is hindered by a lack of comprehen…
How Reliable Are AI-Generated-Text Detectors? An Assessment Framework Using Evasive Soft Prompts
Tharindu Kumarage, Paras Sheth, Raha Moraffah +2
In recent years, there has been a rapid proliferation of AI-generated text, primarily driven by the release of powerful pre-trained language models (PLMs). To address the issue of…
ConDA: Contrastive Domain Adaptation for AI-generated Text Detection
Amrita Bhattacharjee, Tharindu Kumarage, Raha Moraffah +1
Large language models (LLMs) are increasingly being used for generating text in a variety of use cases, including journalistic news articles. Given the potential malicious nature i…
Towards LLM-guided Causal Explainability for Black-box Text Classifiers
Amrita Bhattacharjee, Raha Moraffah, Joshua Garland +1
With the advent of larger and more complex deep learning models, such as in Natural Language Processing (NLP), model qualities like explainability and interpretability, albeit high…
Causality Guided Disentanglement for Cross-Platform Hate Speech Detection
Paras Sheth, Tharindu Kumarage, Raha Moraffah +2
Social media platforms, despite their value in promoting open discourse, are often exploited to spread harmful content. Current deep learning and natural language processing models…
PEACE: Cross-Platform Hate Speech Detection- A Causality-guided Framework
Paras Sheth, Tharindu Kumarage, Raha Moraffah +2
Hate speech detection refers to the task of detecting hateful content that aims at denigrating an individual or a group based on their religion, gender, sexual orientation, or othe…
Domain Generalization -- A Causal Perspective
Paras Sheth, Raha Moraffah, K. Selçuk Candan +2
Machine learning models rely on various assumptions to attain high accuracy. One of the preliminary assumptions of these models is the independent and identical distribution, which…
Evaluation Methods and Measures for Causal Learning Algorithms
Lu Cheng, Ruocheng Guo, Raha Moraffah +3
The convenient access to copious multi-faceted data has encouraged machine learning researchers to reconsider correlation-based learning and embrace the opportunity of causality-ba…