11 papers
Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs
Shrestha Datta, Hongfu Liu, Anshuman Chhabra
Understanding which parameters are influential in Large Language Models (LLMs) is central to improving their efficiency, reliability, and interpretability. We introduce Weight-Adju…
Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models
Shahriar Kabir Nahin, Hadi Askari, Muhao Chen +1
Test-Time Scaling (TTS) improves LLM reasoning by exploring multiple candidate responses and then operating over this set to find the best output. A tacit premise behind TTS is tha…
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
Anshuman Chhabra, Shrestha Datta, Shahriar Kabir Nahin +1
Agentic AI systems powered by large language models (LLMs) and endowed with planning, tool use, memory, and autonomy, are emerging as powerful, flexible platforms for automation. T…
"Whose Side Are You On?" Estimating Ideology of Political and News Content Using Large Language Models and Few-shot Demonstration Selection
Muhammad Haroon, Magdalena Wojcieszak, Anshuman Chhabra
The rapid growth of social media platforms has led to concerns about radicalization, filter bubbles, and content bias. Existing approaches to classifying ideology are limited in th…
Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models
Anshuman Chhabra, Bo Li, Jian Chen +2
A core data-centric learning challenge is the identification of training samples that are detrimental to model performance. Influence functions serve as a prominent tool for this t…
LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions
Hadi Askari, Shivanshu Gupta, Fei Wang +2
Pretrained Large Language Models (LLMs) achieve strong performance across a wide range of tasks, yet exhibit substantial variability in the various layers' training quality with re…