Add jfinqa: Japanese Financial Numerical Reasoning QA#1169
Open
ajtgjmdjp wants to merge 1 commit intohuggingface:mainfrom
Open
Add jfinqa: Japanese Financial Numerical Reasoning QA#1169ajtgjmdjp wants to merge 1 commit intohuggingface:mainfrom
ajtgjmdjp wants to merge 1 commit intohuggingface:mainfrom
Conversation
Three subtasks: numerical reasoning (550), consistency checking (200), and temporal reasoning (250) from 68 companies' EDINET filings. Custom metrics handle Japanese financial formats: fullwidth digits, triangle negatives, kanji multipliers, and unit suffixes. Dataset: https://huggingface.co/datasets/ajtgjmdjp/jfinqa Co-Authored-By: Claude Opus 4.6 <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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds jfinqa (Japanese Financial Numerical Reasoning QA) as a new evaluation task.
Closes #1168
Changes
src/lighteval/tasks/tasks/jfinqa.py: Task file with 3 configs, prompt function, and 2 custom metrics (exact match + numerical match with 1% tolerance)Test plan
pre-commit run --files src/lighteval/tasks/tasks/jfinqa.pypassespython -c "from lighteval.tasks.tasks.jfinqa import TASKS_TABLE"loads 3 tasks🤖 Generated with Claude Code