# Uncovering Representation Bias for Investment Decisions in Open-Source Large Language Models

arXiv: https://arxiv.org/abs/2510.05702 · HTML: https://mlsanity.com/paper/2510.05702/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 22 references that are in the map.
- First posted on arXiv 7 Oct 2025.

## Builds on (most cited first, 10 of 10)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Your AI, Not Your View: The Bias of LLMs in Investment Analysis](https://mlsanity.com/paper/2507.20957/) (2025)
- [Bring Your Own Prompts: Use-Case-Specific Bias and Fairness Evaluation for LLMs](https://mlsanity.com/paper/2407.10853/) (2024)
- [Are LLMs Rational Investors? A Study on Detecting and Reducing the Financial Bias in LLMs](https://mlsanity.com/paper/2402.12713/) (2024)
- [LLM-Enhanced Black-Litterman Portfolio Optimization](https://mlsanity.com/paper/2504.14345/) (2025)
- [Exposing Product Bias in LLM Investment Recommendation](https://mlsanity.com/paper/2503.08750/) (2025)
- [LangFair: A Python Package for Assessing Bias and Fairness in Large Language Model Use Cases](https://mlsanity.com/paper/2501.03112/) (2025)
- [Ensuring Equitable Financial Decisions: Leveraging Counterfactual Fairness and Deep Learning for Bias](https://mlsanity.com/paper/2408.16088/) (2024)
- [Gender Bias of LLM in Economics: An Existentialism Perspective](https://mlsanity.com/paper/2410.19775/) (2024)

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

- [Making LLMs Reliable When It Matters Most: A Five-Layer Architecture for High-Stakes Decisions](https://mlsanity.com/paper/2511.07669/) (2025)
- [Your AI, On a Dial: Controlling Investment Bias in LLMs with a Single Neuron](https://mlsanity.com/paper/2608.22852/) (2026)

## Abstract (arXiv)

Large Language Models are increasingly adopted in financial applications to support investment workflows. However, prior studies have seldom examined how these models reflect biases related to firm size, sector, or financial characteristics, which can significantly impact decision-making. This paper addresses this gap by focusing on representation bias in open-source Qwen models. We propose a balanced round-robin prompting method over approximately 150 U.S. equities, applying constrained decoding and token-logit aggregation to derive firm-level confidence scores across financial contexts. Using statistical tests and variance analysis, we find that firm size and valuation consistently increase model confidence, while risk factors tend to decrease it. Confidence varies significantly across sectors, with the Technology sector showing the greatest variability. When models are prompted for specific financial categories, their confidence rankings best align with fundamental data, moderately with technical signals, and least with growth indicators. These results highlight representation bias in Qwen models and motivate sector-aware calibration and category-conditioned evaluation protocols for safe and fair financial LLM deployment.