Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms

v1v2 (latest)

Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms

23 May 2025

ArXiv (abs)PDF HTML

Papers citing "Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms"

5 / 55 papers shown

Title
Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth Yihe Dong Jean-Baptiste Cordonnier Andreas Loukas 163 388 0 05 Mar 2021
AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts Taylor Shin Yasaman Razeghi Robert L Logan IV Eric Wallace Sameer Singh KELM 117 409 0 29 Oct 2020
RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models Samuel Gehman Suchin Gururangan Maarten Sap Yejin Choi Noah A. Smith 210 1,222 0 24 Sep 2020
Measuring Massive Multitask Language Understanding Dan Hendrycks Collin Burns Steven Basart Andy Zou Mantas Mazeika Basel Alomair Jacob Steinhardt ELM RALM 204 4,580 0 07 Sep 2020
Intrinsic dimension of data representations in deep neural networks A. Ansuini Alessandro Laio Jakob H. Macke D. Zoccolan AI4CE 109 279 0 29 May 2019