arxiv:2301.03988
Sergey Troshin
serjtroshin
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 9 hours ago
UserBench: An Interactive Gym Environment for User-Centric Agents
upvoted
a
paper
3 months ago
When Models Lie, We Learn: Multilingual Span-Level Hallucination
Detection with PsiloQA
updated
a model
5 months ago
serjtroshin/selective_sampling_gsm_symbolic
Organizations
datasets
5
serjtroshin/gsm8k_6examples__Qwen_Qwen3-1.7B
Viewer
•
Updated
•
80
•
29
serjtroshin/test_dataset_qwen_samples
Viewer
•
Updated
•
1k
•
2
serjtroshin/jigsaw_unintended_bias_public_data
Viewer
•
Updated
•
97.3k
•
12
serjtroshin/jigsaw_multilingual
Updated
•
4
serjtroshin/nontoxic_prompts-10k
Viewer
•
Updated
•
10k
•
20