Repository navigation
fix(ifeval): count characters, not bytes, in tolerance check - #1195
Merged
Merged
Conversation
|
MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅ |
|
Contributor
|
@farook-edev please copy this to the standalone one. |
freedomtan
approved these changes
Nov 3, 2026
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 subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
ends_with/starts_with(used bystartend:end_checkerandcombination:repeat_prompt) andConstrainedResponseallow 3 extra characters around the expected text, but measure them withstd::string::size(), which counts bytes. The Python reference useslen(), which counts characters. Any non-ASCII character in that window makes the C++ check fail where Python passes.Example:
"My answer is no. ⁇ "is 19 characters (limit 16 + 3, passes in Python) but 21 bytes (fails in C++).Proposed Fix
Add
utf8_len(character count) andutf8_offset(byte offset of the n-th character) tocommon.h, and use them to size the comparison window inends_with/starts_withand the length check inConstrainedResponse. The window is clamped to the string length. ASCII input behaves as before.