Strings from the Library of Babel: Random Sampling as a Strong Baseline for Prompt Optimisation
This challenges the assumption that effective prompts must be human-readable or task-relevant, providing a strong baseline for prompt optimization research, though it is incremental in nature.
The paper tackled prompt optimization for text classification by showing that randomly sampled token separators can match or exceed the performance of language model-generated and human-curated prompts, with less than 1% difference from self-optimization methods and a 12% average improvement over human baselines across nine tasks.
Recent prompt optimisation approaches use the generative nature of language models to produce prompts -- even rivaling the performance of human-curated prompts. In this paper, we demonstrate that randomly sampling tokens from the model vocabulary as ``separators'' can be as effective as language models for prompt-style text classification. Our experiments show that random separators are competitive baselines, having less than a 1% difference compared to previous self-optimisation methods and showing a 12% average relative improvement over strong human baselines across nine text classification tasks and eight language models. We further analyse this phenomenon in detail using three different random generation strategies, establishing that the language space is rich with potentially good separators, with a greater than 40% average chance that a randomly drawn separator performs better than human-curated separators. These observations challenge the common assumption that an effective prompt should be human readable or task relevant and establish a strong baseline for prompt optimisation research.