Generative Verifiers: Reward Modeling as Next-Token Prediction — mentioned by tekacs

Mon, 14 Jul 2025 00:06:43 GMT

Besides the great subject matter, I love how densely packed this article is with links to relevant papers and materials! (Because I almost missed this) In the comments on the post someone linked to this paper: https://arxiv.org/html/2408.15240v1

Paper and discussion history. A mention is not an endorsement.

Generative Verifiers: Reward Modeling as Next-Token Prediction — mentioned by abrichr

Wed, 28 Aug 2024 05:37:37 GMT

https://arxiv.org/abs/2408.15240 > We demonstrate that when using Gemma-based verifiers on algorithmic and grade-school math reasoning tasks, GenRM outperforms discriminative verifiers and LLM-as-a-Judge, showing a 16-64% improvement in the percentage of problems solved with Best-of-N. Furthermore, we show that GenRM scales favorably across dataset size, model capacity, and inference-time compute.

Paper and discussion history. A mention is not an endorsement.

Generative Verifiers: Reward Modeling as Next-Token Prediction · HackerPapers discussions

Generative Verifiers: Reward Modeling as Next-Token Prediction — mentioned by tekacs

Generative Verifiers: Reward Modeling as Next-Token Prediction — mentioned by abrichr