# Relative Value Biases in Large Language Models

arXiv: https://arxiv.org/abs/2401.14530 · HTML: https://mlsanity.com/paper/2401.14530/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 28 references that are in the map.
- First posted on arXiv 25 Jan 2024.

## Builds on (most cited first, 8 of 8)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Using cognitive psychology to understand GPT-3](https://mlsanity.com/paper/2206.14576/) (2022)
- [Studying and improving reasoning in humans and machines](https://mlsanity.com/paper/2309.12485/) (2023)
- [Aspects of human memory and Large Language Models](https://mlsanity.com/paper/2311.03839/) (2023)

## Built on by (most cited first, 6 of 6)

- [Can large language models explore in-context?](https://mlsanity.com/paper/2403.15371/) (2024)
- [Should You Use Your Large Language Model to Explore or Exploit?](https://mlsanity.com/paper/2502.00225/) (2025)
- [Large Language Models are Biased Reinforcement Learners](https://mlsanity.com/paper/2405.11422/) (2024)
- [LLM Agents Display Human Biases but Exhibit Distinct Learning Patterns](https://mlsanity.com/paper/2503.10248/) (2025)
- [Mind the (DH) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLMs](https://mlsanity.com/paper/2602.15173/) (2026)
- [Financial Stability Implications of Generative AI: Taming the Animal Spirits](https://mlsanity.com/paper/2510.01451/) (2025)

## Abstract (arXiv)

Studies of reinforcement learning in humans and animals have demonstrated a preference for options that yielded relatively better outcomes in the past, even when those options are associated with lower absolute reward. The present study tested whether large language models would exhibit a similar bias. We had gpt-4-1106-preview (GPT-4 Turbo) and Llama-2-70B make repeated choices between pairs of options with the goal of maximizing payoffs. A complete record of previous outcomes was included in each prompt. Both models exhibited relative value decision biases similar to those observed in humans and animals. Making relative comparisons among outcomes more explicit magnified the bias, whereas prompting the models to estimate expected outcomes caused the bias to disappear. These results have implications for the potential mechanisms that contribute to context-dependent choice in human agents.