One Token to Fool LLM-as-a-Judge
Paper
•
2507.08794
•
Published
•
31
Haolin Liu
lhl616
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
3 days ago
Beyond Correctness: Harmonizing Process and Outcome Rewards through RL
Training
upvoted
a
paper
11 days ago
Self-Rewarding Vision-Language Model via Reasoning Decomposition
upvoted
a
paper
about 1 month ago
Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback
Organizations
None yet
authored
a
paper
about 2 months ago