Soumya Saha

thesoum's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 8 months ago

AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning

Paper • 2505.16400 • Published May 22, 2025 • 35

upvoted 2 papers over 1 year ago

JudgeBench: A Benchmark for Evaluating LLM-based Judges

Paper • 2410.12784 • Published Oct 16, 2024 • 47

Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge

Paper • 2407.19594 • Published Jul 28, 2024 • 21

upvoted 2 papers about 2 years ago

Chain-of-Verification Reduces Hallucination in Large Language Models

Paper • 2309.11495 • Published Sep 20, 2023 • 39

Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model

Paper • 2310.09520 • Published Oct 14, 2023 • 11