# Intentional Biases in LLM Responses

arXiv: https://arxiv.org/abs/2311.07611 · HTML: https://mlsanity.com/paper/2311.07611/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 16 references that are in the map.
- First posted on arXiv 11 Nov 2023.

## Builds on (most cited first, 11 of 11)

- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only](https://mlsanity.com/paper/2306.01116/) (2023)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models](https://mlsanity.com/paper/2305.18189/) (2023)
- [Efficient Large Scale Language Modeling with Mixtures of Experts](https://mlsanity.com/paper/2112.10684/) (2021)
- [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023)
- [Ask Me Anything: A simple strategy for prompting language models](https://mlsanity.com/paper/2210.02441/) (2022)
- [Hallucinations in Large Multilingual Translation Models](https://mlsanity.com/paper/2303.16104/) (2023)
- [AI Text-to-Behavior: A Study In Steerability](https://mlsanity.com/paper/2308.07326/) (2023)

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

- [Safeguarding Large Language Models: A Survey](https://mlsanity.com/paper/2406.02622/) (2024)
- [Building Guardrails for Large Language Models](https://mlsanity.com/paper/2402.01822/) (2024)

## Abstract (arXiv)

In this study we intentionally introduce biases into large language model responses in an attempt to create specific personas for interactive media purposes. We explore the differences between open source models such as Falcon-7b and the GPT-4 model from Open AI, and we quantify some differences in responses afforded by the two systems. We find that the guardrails in the GPT-4 mixture of experts models with a supervisor, while useful in assuring AI alignment in general, are detrimental in trying to construct personas with a variety of uncommon viewpoints. This study aims to set the groundwork for future exploration in intentional biases of large language models such that these practices can be applied in the creative field, and new forms of media.