# Your AI, On a Dial: Controlling Investment Bias in LLMs with a Single Neuron

arXiv: https://arxiv.org/abs/2608.22852 · HTML: https://mlsanity.com/paper/2608.22852/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Builds on (most cited first, 19 of 19)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021)
- [Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts](https://mlsanity.com/paper/1307.5336/) (2013)
- [Analyzing the Generalization and Reliability of Steering Vectors](https://mlsanity.com/paper/2407.12404/) (2024)
- [Steering Without Side Effects: Improving Post-Deployment Control of Language Models](https://mlsanity.com/paper/2406.15518/) (2024)
- [FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering](https://mlsanity.com/paper/2504.14492/) (2025)
- [Your AI, Not Your View: The Bias of LLMs in Investment Analysis](https://mlsanity.com/paper/2507.20957/) (2025)
- [Decision-informed Neural Networks with Large Language Model Integration for Portfolio Optimization](https://mlsanity.com/paper/2502.00828/) (2025)
- [Evaluating LLMs in Finance Requires Explicit Bias Consideration](https://mlsanity.com/paper/2602.14233/) (2026)
- [Behavioral Economics of AI: LLM Biases and Corrections](https://mlsanity.com/paper/2602.09362/) (2026)
- [LLM-Enhanced Black-Litterman Portfolio Optimization](https://mlsanity.com/paper/2504.14345/) (2025)
- [The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models](https://mlsanity.com/paper/2406.10130/) (2024)
- [Exposing Product Bias in LLM Investment Recommendation](https://mlsanity.com/paper/2503.08750/) (2025)
- [Uncovering Representation Bias for Investment Decisions in Open-Source Large Language Models](https://mlsanity.com/paper/2510.05702/) (2025)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used in investment decision-making, yet prior work shows that they exhibit systematic, model-specific investment preferences. We study whether a model's overall investment stance can be calibrated to a specified direction and strength. We introduce an investment-bias dial, an inference-time intervention on a single neuron that continuously adjusts a model-level decision prior---its overall tendency toward buying or selling---without targeting specific firms or investment attributes. Using matched positive and negative evidence, we evaluate five open-weight LLMs and find that the dial produces monotonic changes in investment stance without modifying prompts or model parameters. At the response level, the dial shifts both investment decisions and the evidential emphasis of generated rationales under identical inputs. In an agentic retrieval setting, the dial also changes what information the model searches for, which evidence it selects, and which evidence is reflected in its final analysis. In a long-context evaluation, the dial maintains stable stance control as context length increases, whereas a matched system-prompt instruction progressively attenuates. We further show that changes in the dial propagate to security rankings and downstream portfolio composition in an exploratory backtest. Overall, our results show that an LLM's aggregate investment stance can be calibrated toward a specified target at inference time.