# Utility-inspired Reward Transformations Improve Reinforcement Learning Training of Language Models

arXiv: https://arxiv.org/abs/2501.06248 · HTML: https://mlsanity.com/paper/2501.06248/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 8 Jan 2025.

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)
- [A Long Way to Go: Investigating Length Correlations in RLHF](https://mlsanity.com/paper/2310.03716/) (2023)
- [Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking](https://mlsanity.com/paper/2312.09244/) (2023)
- [WARM: On the Benefits of Weight Averaged Reward Models](https://mlsanity.com/paper/2401.12187/) (2024)
- [A Minimaximalist Approach to Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2401.04056/) (2024)
- [Evaluating and Mitigating Discrimination in Language Model Decisions](https://mlsanity.com/paper/2312.03689/) (2023)
- [Confronting Reward Model Overoptimization with Constrained RLHF](https://mlsanity.com/paper/2310.04373/) (2023)
- [Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation](https://mlsanity.com/paper/2407.10817/) (2024)
- [Axioms for AI Alignment from Human Feedback](https://mlsanity.com/paper/2405.14758/) (2024)
- [The Consensus Game: Language Model Generation via Equilibrium Search](https://mlsanity.com/paper/2310.09139/) (2023)
- [Attention Flows are Shapley Value Explanations](https://mlsanity.com/paper/2105.14652/) (2021)
- [Steering Language Models with Game-Theoretic Solvers](https://mlsanity.com/paper/2402.01704/) (2024)

## Built on by (most cited first, 2 of 2)

- [Robust Multi-Objective Controlled Decoding of Large Language Models](https://mlsanity.com/paper/2503.08796/) (2025)
- [Quark Medical Alignment: A Holistic Multi-Dimensional Alignment and Collaborative Optimization Paradigm](https://mlsanity.com/paper/2602.11661/) (2026)

## Abstract (arXiv)

Current methods that train large language models (LLMs) with reinforcement learning feedback, often resort to averaging outputs of multiple rewards functions during training. This overlooks crucial aspects of individual reward dimensions and inter-reward dependencies that can lead to sub-optimal outcomes in generations. In this work, we show how linear aggregation of rewards exhibits some vulnerabilities that can lead to undesired properties of generated text. We then propose a transformation of reward functions inspired by economic theory of utility functions (specifically Inada conditions), that enhances sensitivity to low reward values while diminishing sensitivity to already high values. We compare our approach to the existing baseline methods that linearly aggregate rewards and show how the Inada-inspired reward feedback is superior to traditional weighted averaging. We quantitatively and qualitatively analyse the difference in the methods, and see that models trained with Inada-transformations score as more helpful while being less harmful.