# Better Language Model-Based Judging Reward Modeling through Scaling Comprehension Boundaries

arXiv: https://arxiv.org/abs/2508.18212 · HTML: https://mlsanity.com/paper/2508.18212/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 37 of its 59 references that are in the map.
- First posted on arXiv 25 Aug 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)

## Builds on (most cited first, 30 of 37)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [Prometheus: Inducing Fine-grained Evaluation Capability in Language Models](https://mlsanity.com/paper/2310.08491/) (2023)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (2024)
- [Understanding Dataset Difficulty with V-Usable Information](https://mlsanity.com/paper/2110.08420/) (2021)
- [Large Language Model Alignment: A Survey](https://mlsanity.com/paper/2309.15025/) (2023)
- [Inference-Time Scaling for Generalist Reward Modeling](https://mlsanity.com/paper/2504.02495/) (2025)
- [Secrets of RLHF in Large Language Models Part II: Reward Modeling](https://mlsanity.com/paper/2401.06080/) (2024)
- [BERT: A Review of Applications in Natural Language Processing and Understanding](https://mlsanity.com/paper/2103.11943/) (2021)
- [GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning](https://mlsanity.com/paper/2504.00891/) (2025)
- [OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning](https://mlsanity.com/paper/2311.09724/) (2023)
- [A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias](https://mlsanity.com/paper/2404.00929/) (2024)
- [Aligning Large Language Models with Representation Editing: A Control Perspective](https://mlsanity.com/paper/2406.05954/) (2024)
- [RMB: Comprehensively Benchmarking Reward Models in LLM Alignment](https://mlsanity.com/paper/2410.09893/) (2024)
- [One Token to Fool LLM-as-a-Judge](https://mlsanity.com/paper/2507.08794/) (2025)

## Built on by (most cited first, 1 of 1)

- [Indirect Question Answering in English, German and Bavarian: A Challenging Task for High- and Low-Resource Languages Alike](https://mlsanity.com/paper/2603.15130/) (2026)

## Abstract (arXiv)

The emergence of LM-based judging reward modeling, represented by generative reward models, has successfully made reinforcement learning from AI feedback (RLAIF) efficient and scalable. To further advance this paradigm, we propose a core insight: this form of reward modeling shares fundamental formal consistency with natural language inference (NLI), a core task in natural language understanding. This reframed perspective points to a key path for building superior reward models: scaling the model's comprehension boundaries. Pursuing this path, exploratory experiments on NLI tasks demonstrate that the slot prediction masked language models (MLMs) incorporating contextual explanations achieve significantly better performance compared to mainstream autoregressive models. Based on this key finding, we propose ESFP-RM, a two-stage LM-based judging reward model that utilizes an explanation based slot framework for prediction to fully leverage the advantages of MLMs. Extensive experiments demonstrate that in both reinforcement learning from human feedback (RLHF) and out-of-distribution (OOD) scenarios, the ESFP-RM framework delivers more stable and generalizable reward signals compared to generative reward models.