14,970
edits
LLMs Usage FAQ: Difference between revisions
Jump to navigation
Jump to search
m
→Can AI Self-Verify Its Reasoning Errors?
| Line 213: | Line 213: | ||
Method 2: Structured Reasoning Step Prompts | Method 2: Structured Reasoning Step Prompts | ||
When using the same model rather than more advanced reasoning models, you can require the AI to execute a key step before reaching conclusions: "Before making your final conclusion, please list all evidence supporting this conclusion in complete detail, ranked from highest to lowest relevance. Then answer the question based on these evidence paragraphs." | When using the same model rather than more advanced reasoning models, you can require the AI to execute a key step before reaching conclusions: "Before making your final conclusion, please list all evidence supporting this conclusion in complete detail, ranked from highest to lowest relevance. Then answer the question based on these evidence paragraphs." This technique is not recommended for "reasoning models", as they already incorporate systematic reasoning processes. <ref>[https://sophiehundertmark.medium.com/new-prompting-rules-when-using-reasoning-models-deep-research-3810ea97bef3 New prompting rules when using reasoning models (Deep Research) | by Sophie Hundertmark | Medium] "Avoid chain-of-thought (CoT) prompting"</ref> {{exclaim}}. | ||
Method 3: Web Data Verification Combined with Structured Reasoning | Method 3: Web Data Verification Combined with Structured Reasoning | ||