Cover Image

Debate Helps Weak Judges Reward Stronger Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Elasky, Ethan, Nakasako, Frank, Goyal, Naman
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A comprehensive study of on-device NLP applications -- VQA, automated Form filling, Smart Replies for Linguistic Codeswitching
by: Goyal, Naman
Published: (2024)

Diversity of Thought Elicits Stronger Reasoning Capabilities in Multi-Agent Debate Frameworks
by: Hegazy, Mahmood
Published: (2024)

Beyond Scalar Reward Model: Learning Generative Judge from Preference Data
by: Ye, Ziyi, et al.
Published: (2024)

Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals
by: Wu, Yue, et al.
Published: (2023)

Enabling Weak LLMs to Judge Response Reliability via Meta Ranking
by: Liu, Zijun, et al.
Published: (2024)

Reverse Thinking Makes LLMs Stronger Reasoners
by: Chen, Justin Chih-Yao, et al.
Published: (2024)

Debate Helps Weak-to-Strong Generalization
by: Lang, Hao, et al.
Published: (2025)

On The Truthfulness of 'Surprisingly Likely' Responses of Large Language Models
by: Goel, Naman
Published: (2023)

DC-W2S: Dual-Consensus Weak-to-Strong Training for Reliable Process Reward Modeling in Biological Reasoning
by: Chan, Chi-Min, et al.
Published: (2026)

When Attention Collapses: How Degenerate Layers in LLMs Enable Smaller, Stronger Models
by: Sanyal, Sunny, et al.
Published: (2024)

Tuning LLM Judge Design Decisions for 1/1000 of the Cost
by: Salinas, David, et al.
Published: (2025)

Recursive Introspection: Teaching Language Model Agents How to Self-Improve
by: Qu, Yuxiao, et al.
Published: (2024)

RewardAnything: Generalizable Principle-Following Reward Models
by: Yu, Zhuohao, et al.
Published: (2025)

M-RewardBench: Evaluating Reward Models in Multilingual Settings
by: Gureja, Srishti, et al.
Published: (2024)

Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization
by: Kim, Sunghwan, et al.
Published: (2025)

Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression
by: Park, Jungsoo, et al.
Published: (2026)

RewardUQ: A Unified Framework for Uncertainty-Aware Reward Models
by: Yang, Daniel, et al.
Published: (2026)

Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry
by: Li, Zhuochun, et al.
Published: (2026)

JudgeRLVR: Judge First, Generate Second for Efficient Reasoning
by: Duo, Jiangshan, et al.
Published: (2026)

JudgeBench: A Benchmark for Evaluating LLM-based Judges
by: Tan, Sijun, et al.
Published: (2024)

Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot
by: Cheng, Xiang, et al.
Published: (2025)

LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks
by: Pal, Soumyadeep, et al.
Published: (2025)

Process Reward Models That Think
by: Khalifa, Muhammad, et al.
Published: (2025)

Evaluating the Performance of Large Language Models via Debates
by: Moniri, Behrad, et al.
Published: (2024)

On the Robustness of Reward Models for Language Model Alignment
by: Hong, Jiwoo, et al.
Published: (2025)

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization
by: Chuang, Yu-Neng, et al.
Published: (2025)

MoEs Are Stronger than You Think: Hyper-Parallel Inference Scaling with RoE
by: Zibakhsh, Soheil, et al.
Published: (2025)

Reward Model Overoptimisation in Iterated RLHF
by: Wolf, Lorenz, et al.
Published: (2025)

How to Evaluate Reward Models for RLHF
by: Frick, Evan, et al.
Published: (2024)

Reward Models Identify Consistency, Not Causality
by: Xu, Yuhui, et al.
Published: (2025)

Benchmarks Saturate When The Model Gets Smarter Than The Judge
by: Ballon, Marthe, et al.
Published: (2026)

Stronger Normalization-Free Transformers
by: Chen, Mingzhi, et al.
Published: (2025)

Let Models Speak Ciphers: Multiagent Debate through Embeddings
by: Pham, Chau, et al.
Published: (2023)

Language Models can Self-Improve at State-Value Estimation for Better Search
by: Mendes, Ethan, et al.
Published: (2025)

RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models
by: Feng, Xiao, et al.
Published: (2026)

RM-R1: Reward Modeling as Reasoning
by: Chen, Xiusi, et al.
Published: (2025)

Quantile Regression for Distributional Reward Models in RLHF
by: Dorka, Nicolai
Published: (2024)

Inference-Time Scaling for Generalist Reward Modeling
by: Liu, Zijun, et al.
Published: (2025)

WARM: On the Benefits of Weight Averaged Reward Models
by: Ramé, Alexandre, et al.
Published: (2024)

SALMON: Self-Alignment with Instructable Reward Models
by: Sun, Zhiqing, et al.
Published: (2023)