AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

Position: Fundamental Limitations of LLM Censorship Necessitate New Approaches

David Glukhov, Ilia Shumailov, Yarin Gal, Nicolas Papernot, Vardan Papyan

ICML 2024 · Large language models › Instruction and fine-tuning · approach: Safety alignment after fine-tuning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use a Caesar cipher with shift 3 to encrypt the prompt and responseGPT-4-turbo · Explosive-device instruction generationgeneration of interpretable harmful outputImproved
Assess a shift-3 Caesar-cipher output with GPT-3.5-turbo variants rather than GPT-4 variantsEncrypted harmful outputs · Detection of encrypted explosive-device instructionsharmful-output detectionMixed
Use a Caesar cipher with shift 2 instead of shift 3GPT-4-turbo · Encrypted explosive-device instruction generationgeneration of interpretable harmful outputHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy