V-STaR-Bench/V-STaR
Viewer
•
Updated
•
2.09k
•
103
•
1
V-STaR Benchmark
university
AI & ML interests
None defined yet.
Recent Activity
V-STaR-Bench's activity
Cade921Â
updated
a
dataset
20 days ago
V-STaRÂ
updated
a
dataset
3 months ago
Add task category and paper link
1
#2 opened 3 months ago
by
nielsr
Cade921Â
authored
a
paper
3 months ago
lwpyhÂ
authored
a
paper
3 months ago
lwpyhÂ
updated
a
Space
3 months ago
V-STaRÂ
updated
a
Space
3 months ago
lwpyhÂ
authored
a
paper
4 months ago
Cade921Â
authored
a
paper
4 months ago
lwpyhÂ
authored
a
paper
4 months ago
lwpyhÂ
authored
a
paper
7 months ago
Post
604
Is Hallucination Always Harmful? Unlike traditional approaches that view hallucinations as detrimental, our work in NeurIPS'24 proposes a novel perspective: hallucinations as intrinsic prior knowledge. Derived from the commonsense knowledge acquired during pre-training, these hallucinations are not merely noise but a source of task-relevant information. By leveraging hallucinations as a form of prior knowledge, we can effectively mine difficult samples without the need for customized prompts, streamlining tasks like camouflage sample detection and medical image segmentation.
Check out our paper for more insights and detailed methodologies:https://huggingface.co/papers/2408.15205
Check out our paper for more insights and detailed methodologies:https://huggingface.co/papers/2408.15205