Why are LLM_evaluator.py and LMM_evaluator.py the same?

[benj617]

Thanks for your excellent work!
I noticed that Evaluation/srcs/LLM_evaluator.py and Evaluation/srcs/LMM_evaluator.py appear to be identical. Is this intentional?
I would expect LMM_evaluator.py to accept chart images as input for visual comparison, rather than code-based evaluation. Could you clarify if this is planned or if there might have been an upload oversight?
Thanks!

[accebet]

Hi, sorry for the late reply.

You’re right — this was an issue in the previous version. I’ve now updated all the evaluation scripts, including the LMM evaluator. The updated evaluation code is more comprehensive and covers a broader range of evaluation aspects. Please refer to the latest version of the code for the corrected implementation.

Thanks again for your careful review!