# Large Language Models are Biased Reinforcement Learners

arXiv: https://arxiv.org/abs/2405.11422 · HTML: https://mlsanity.com/paper/2405.11422/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 50 references that are in the map.
- First posted on arXiv 19 May 2024.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [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 Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (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)
- [LanguageMPC: Large Language Models as Decision Makers for Autonomous Driving](https://mlsanity.com/paper/2310.03026/) (2023)
- [Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods](https://mlsanity.com/paper/2404.00282/) (2024)
- [CogBench: a large language model walks into a psychology lab](https://mlsanity.com/paper/2402.18225/) (2024)
- [Studying and improving reasoning in humans and machines](https://mlsanity.com/paper/2309.12485/) (2023)
- [In-context learning agents are asymmetric belief updaters](https://mlsanity.com/paper/2402.03969/) (2024)
- [Relative Value Biases in Large Language Models](https://mlsanity.com/paper/2401.14530/) (2024)

## Built on by (most cited first, 5 of 5)

- [Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models](https://mlsanity.com/paper/2410.01280/) (2024)
- [Towards Reward Fairness in RLHF: From a Resource Allocation Perspective](https://mlsanity.com/paper/2505.23349/) (2025)
- [Beyond Nash Equilibrium: Bounded Rationality of LLMs and humans in Strategic Decision-making](https://mlsanity.com/paper/2506.09390/) (2025)
- [ORCH: many analyses, one merge-a deterministic multi-agent orchestrator for discrete-choice reasoning with EMA-guided routing](https://mlsanity.com/paper/2602.01797/) (2026)
- [PAFO: Pareto Fairness Optimization for Personalized Reward Modeling](https://mlsanity.com/paper/2606.07988/) (2026)

## Abstract (arXiv)

In-context learning enables large language models (LLMs) to perform a variety of tasks, including learning to make reward-maximizing choices in simple bandit tasks. Given their potential use as (autonomous) decision-making agents, it is important to understand how these models perform such reinforcement learning (RL) tasks and the extent to which they are susceptible to biases. Motivated by the fact that, in humans, it has been widely documented that the value of an outcome depends on how it compares to other local outcomes, the present study focuses on whether similar value encoding biases apply to how LLMs encode rewarding outcomes. Results from experiments with multiple bandit tasks and models show that LLMs exhibit behavioral signatures of a relative value bias. Adding explicit outcome comparisons to the prompt produces opposing effects on performance, enhancing maximization in trained choice sets but impairing generalization to new choice sets. Computational cognitive modeling reveals that LLM behavior is well-described by a simple RL algorithm that incorporates relative values at the outcome encoding stage. Lastly, we present preliminary evidence that the observed biases are not limited to fine-tuned LLMs, and that relative value processing is detectable in the final hidden layer activations of a raw, pretrained model. These findings have important implications for the use of LLMs in decision-making applications.