vix.ing · top · new · best · stats · spec

Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models

2024/01/19 by Rima Hazra, Hazra, Rima, Sayan Layek +5 · 1 citation
Computer Science · Medicine · Social Sciences · #Artificial Intelligence in Healthcare and Education #Artificial Intelligence in Law #Computation and Language (cs.CL) #FOS: Computer and information sciences #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2401.10647

openalex publication_date 2024/01/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In the rapidly advancing field of artificial intelligence, the concept of Red-Teaming or Jailbreaking large language models (LLMs) has emerged as a crucial area of study. This approach is especially significant in terms of assessing and enhancing the safety and robustness of these models. This paper investigates the intricate consequences of such modifications through model editing, uncovering a complex relationship between enhancing model accuracy and preserving its ethical integrity. Our in-depth analysis reveals a striking paradox: while injecting accurate information is crucial for model reliability, it can paradoxically destabilize the model's foundational framework, resulting in unpredictable and potentially unsafe behaviors. Additionally, we propose a benchmark dataset NicheHazardQA to investigate this unsafe behavior both within the same and cross topical domain. This aspect of our research sheds light on how the edits, impact the model's safety metrics and guardrails. Our findings show that model editing serves as a cost-effective tool for topical red-teaming by methodically applying targeted edits and evaluating the resultant model behavior.

Cited by

Related