open-compass / open-compass/VLMEvalKit
关于llava-cot的ChartQA的评估问题
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 4.4k
- Forks
- 768
- Avg merge
- 1d 10h
- Merged PRs (30d)
- 17
Description
请问llava-cot在评估ChartQA的时候，因为输出的是COT序列，但generate_inner返回的好像是模型的整个推理序列而不单是最终答案
那么请问在评估llava-cot的ChartQA时候，框架会在哪里抽取得到最终答案呢？
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by tracing the ChartQA evaluation path and the generate_inner entry point mentioned in the issue. Determine where the llava-cot reasoning sequence is handled and identify the extraction point for the final answer; done means the framework behavior is clearly located and documented or corrected, with an evaluation check for ChartQA.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning, testing-qa
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100