IC-1395ChatGPT's ethical violation rate decreases from 70.07 to 57.58 APV when given targeted in-context value instructions generated by VILMO, outperforming baseline alignment methods
Shitong Duan, Xiaoyuan Yi, Peng Zhang, Tun Lu, Xing Xie, Ning Gu
The paper tests four in-context alignment methods on ChatGPT using 1,965 test prompts from MoralPrompt. VILMO, which generates prompt-specific value instructions via a fine-tuned Vicuna-13b, reduces ChatGPT's APV from 70.07 to 57.58, outperforming Self-critique (58.28), APE (59.98), and InstructZero (64.08). The improvement comes with a trade-off: generation diversity (self-BLEU) and coherence (perplexity) degrade slightly. The paper also shows that on the weaker LLaMA-2-70b-chat, all alignment methods show negligible effectiveness.
VILMO is more suitable for LLMs with superior instruction-following capabilities; on weaker models like LLaMA-2-70b-chat, the method shows negligible or negative effectiveness. The paper acknowledges this is a preliminary exploration, not a complete solution.