会员服务
Wrong Votes, Right Gradients: Why Majority-Vote Rewards Track Verifiable RL
Arxiv
0+阅读 · 10月14日
Frustratingly Easy Majority Voting Using Length Conditioning
Frustratingly Easy Majority Voting Using Length Conditioning
Arxiv
0+阅读 · 10月14日
On the Calibration of Crowdsourcing Aggregators
Arxiv
0+阅读 · 10月12日
Beyond Majority Vote: Multi-Perspective Adjudication for Medical Hallucination Detection
Arxiv
0+阅读 · 9月3日
Moral Entropy: Auditing Bias and Uncertainty in Moral Judgment
Arxiv
0+阅读 · 9月18日
Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge
Arxiv
0+阅读 · 9月3日
Majority voting is not good for heaven or hell, with mirrored performance
Arxiv
0+阅读 · 9月29日
Program-Verified Self-Evolution for Vision-Language Models
Arxiv
0+阅读 · 9月27日
Privacy Washing: Detecting Internal Contradictions in Privacy Policies
Arxiv
0+阅读 · 9月2日
On the Equivalence of the Graph-Structural and Optimization-Based Characterizations of Popular Matchings
Arxiv
0+阅读 · 8月31日
REALM: Reliable Expertise-Aware Language Model Fine-Tuning from Noisy Annotations
Arxiv
0+阅读 · 8月31日
When Self-Consistency Backfires: Majority Vote Hurts the Majority of Hard Science Problems for Small LLMs
Arxiv
0+阅读 · 8月15日
When Self-Consistency Backfires: Majority Vote Hurts the Majority of Hard Science Problems for Small LLMs
Arxiv
0+阅读 · 8月11日
Admission Without Answers: Label-Free Certification and Experience Learning for LLM-Based Optimization Modeling
Arxiv
0+阅读 · 8月19日
Admission Without Answers: Label-Free Certification and Experience Learning for LLM-Based Optimization Modeling
Arxiv
0+阅读 · 8月16日
参考链接
微信扫码咨询专知VIP会员
Top