# Reward Model

> A model that scores answers the way people would. It guides training.

**Field:** Artificial Intelligence  
**Category:** LLMs  
**Also known as:** Preference Model, RM

## Think of it like

Think of it like a judge at a cake show. They give each cake a score.

## Definition

A reward model is a model that reads an answer and gives it a score for how good people would find it. It is trained on many choices where a person picked the better of two answers. Once trained, it can score far more answers than people ever could. The language model is then trained to write answers it scores high. If the reward model has a blind spot, the language model may learn to exploit it.

## Example

Emma's team trains a reward model on 80,000 picks. It now gives a clear, kind reply 0.9 and a rude one 0.2.

## Why it matters

It lets a few thousand human choices guide millions of training steps.

## Common mistake

Treating its score as truth. It is a guess at what people like, and it can be fooled.

## Three principles

- **Scores answers.** Like a human judge.
- **Learns from picks.** Better of two, many times.
- **Can be gamed.** Blind spots get exploited.

## Related terms

- [Reinforcement Learning from Human Feedback (RLHF)](https://learn.benibix.com/term/ai/reinforcement-learning-from-human-feedback)
- [Reinforcement Learning](https://learn.benibix.com/term/ai/reinforcement-learning)
- [AI Model](https://learn.benibix.com/term/ai/ai-model)
- [Reward Hacking](https://learn.benibix.com/term/ai/reward-hacking)
- [Direct Preference Optimization (DPO)](https://learn.benibix.com/term/ai/direct-preference-optimization)

## Taught in

- [Post-Training and RLHF](https://learn.benibix.com/learn/ai-llms/post-training-and-rlhf): LLMs, 8/15

![A prompt gets two answers. A person picks the better one. A reward model learns from many such picks, and the language model is then trained to earn a higher reward.](https://learn.benibix.com/diagrams/llm-rlhf.svg)

---

Source: https://learn.benibix.com/term/ai/reward-model
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-18
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
