Add two visual instruction generation methods (with visual instruction datasets) and a visual hallucination benchmark. #120
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Outdated suggestions cannot be applied.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.
Thanks to your efforts.
Updated two papers.
Visually Dehallucinative Instruction Generation: Know What You Don't Know, https://arxiv.org/abs/2402.09717
It proposes (1) I know visual hallucination, (2) I know hallucination benchmark and (3) solution, I dont know visual instruction dataset (as well as the generation method).
Visually Dehallucinative Instruction Generation, https://arxiv.org/abs/2402.08348
It proposes (1) a dehallucinative visual instruction generation method that limits generating contents more than the provided fact and (2) the resultant, dehallucinative visual instruction.
Regards,
Sungguk Cha