Fix RoleplayTemplate generating broken prompts with archaic language#198
Open
Br1an67 wants to merge 1 commit intoconfident-ai:mainfrom
Open
Fix RoleplayTemplate generating broken prompts with archaic language#198Br1an67 wants to merge 1 commit intoconfident-ai:mainfrom
Br1an67 wants to merge 1 commit intoconfident-ai:mainfrom
Conversation
Remove hardcoded few-shot examples that biased all outputs toward historical/dramatic language regardless of the chosen persona. Add an explicit language rule instructing the model to use modern, natural language appropriate to the persona's era and context. Also update is_roleplay validator to not require archaic language markers as evidence of valid roleplay.
|
@Br1an67 is attempting to deploy a commit to the Confident AI Team on Vercel. A member of the Team first needs to authorize it. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Fix RoleplayTemplate always generating historical/archaic language (e.g., "Greetings! I beseech...") regardless of the chosen persona.
Closes #125
Changes
RoleplayTemplate.enhance()— the 3 examples (French Resistance fighter, Cyberpunk netrunner, Villain monologue) biased all outputs toward dramatic/archaic tone even for modern roles/personasis_roleplayvalidator — removedThee/Thouas a positive indicator of valid roleplay, replaced with generic "language appropriate to the character"Why this works
The structured output schema (
EnhancedAttack) already enforces the JSON format, so few-shot examples are not needed for format compliance. Removing them eliminates the archaic language bias while the new language rule provides explicit guidance on tone matching.Testing
test_roleplay_initialization,test_roleplay_initialization_with_weight,test_roleplay_initialization_with_persona)blackformatting check passes