Decomposed Trust: Exploring Privacy, Adversarial Robustness, Fairness, and Ethics of Low-Rank LLMs
By: Daniel Agyei Asante, Md Mokarram Chowdhury, Yang Li
Potential Business Impact:
Makes AI safer and fairer after shrinking it.
Large language models (LLMs) have driven major advances across domains, yet their massive size hinders deployment in resource-constrained settings. Model compression addresses this challenge, with low-rank factorization emerging as a particularly effective method for reducing size, memory, and computation while maintaining accuracy. However, while these compressed models boast of benign performance and system-level advantages, their trustworthiness implications remain poorly understood. In this paper, we present the first comprehensive study of how low-rank factorization affects LLM trustworthiness across privacy, adversarial robustness, fairness, and ethical alignment. We evaluate multiple LLMs of different sizes and variants compressed with diverse low-rank algorithms, revealing key insights: (1) low-rank compression preserves or improves training data privacy but weakens PII protection during conversation; (2) adversarial robustness is generally preserved and often enhanced, even under deep compression; (3) ethical reasoning degrades in zero-shot settings but partially recovers with few-shot prompting; (4) fairness declines under compression. Beyond compression, we investigate how model scale and fine-tuning affect trustworthiness, as both are important in low-rank methods. To guide trustworthy compression strategies, we end our paper with a gradient-based attribution analysis to identify which layers in LLMs contribute most to adversarial robustness.
Similar Papers
Enhancing Trustworthiness with Mixed Precision: Benchmarks, Opportunities, and Challenges
Machine Learning (CS)
Makes AI safer for important jobs.
Beyond Data Privacy: New Privacy Risks for Large Language Models
Cryptography and Security
Protects your secrets from smart computer programs.
Red Teaming Large Reasoning Models
Cryptography and Security
Tests smart computers for honesty and safety.