Show HN: A surprisingly effective way to predict token importance in LLM prompts https://ift.tt/Xq2zLn9

Show HN: A surprisingly effective way to predict token importance in LLM prompts We explored a novel method to gauge the significance of tokens in prompts given to large language models, without needing direct model access. Essentially, we just did an ablation study on the prompt using cosine similarity of the embeddings as the measure. We got surprisingly promising results when comparing this really simple approach to integrated gradients. Curious to hear thoughts from the community! https://ift.tt/k1Eqcpb September 11, 2023 at 10:59PM