Fix moderation only checking left model's conversation in arena battles#3850
Open
Chessing234 wants to merge 1 commit intolm-sys:mainfrom
Open
Fix moderation only checking left model's conversation in arena battles#3850Chessing234 wants to merge 1 commit intolm-sys:mainfrom
Chessing234 wants to merge 1 commit intolm-sys:mainfrom
Conversation
all_conv_text_right reads from states[0] (left model) instead of states[1] (right model), so the right model's conversation is never moderation-checked. This is a copy-paste error — the named arena file (gradio_block_arena_named.py) correctly uses states[1]. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Bug
In
gradio_block_arena_anony.pyandgradio_block_arena_vision_named.py,all_conv_text_rightreads fromstates[0](left model) instead ofstates[1](right model):This means the right model's conversation is never passed to the moderation filter, allowing policy-violating content through unchecked.
Root cause
Copy-paste error. The correct version exists in
gradio_block_arena_named.py(line 182), which usesstates[1].Fix
Change
states[0]→states[1]forall_conv_text_rightin both files.🤖 Generated with Claude Code