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

• URL: http://arxiv.org/abs/2608.22852v1
• Date: Mon, 24 Aug 2026 06:33:02 GMT
• Title: Your AI, On a Dial: Controlling Investment Bias in LLMs with a Single Neuron
• Abstract summary: We study whether a model's overall investment stance can be calibrated to a specified direction and strength.<n>We introduce an investment-bias dial, an inference-time intervention on a single neuron.<n>We find that the dial produces monotonic changes in investment stance without modifying prompts or model parameters.
• Score: 76.4407829130164
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• One Size Fits None: Heuristic Collapse in LLM Investment Advice [0.0]
  Large language models are increasingly deployed as advisors in high-stakes domains.<n>We investigate whether frontier LLMs actually do this, or whether they instead exhibit collapse.<n>We find that investment allocation decisions are largely determined by self-reported risk tolerance, while other relevant factors contribute minimally.
  arXiv  Detail & Related papers  (2026-04-26T18:45:11Z)
• High-Stakes Personalization: Rethinking LLM Customization for Individual Investor Decision-Making [0.0]
  We argue that individual investor decision-making presents a uniquely challenging domain for LLM personalization.<n>We identify four axes along which individual investing exposes fundamental limitations in standard LLM customization.<n>We propose open research directions for personalized NLP in high-stakes, temporally extended decision domains.
  arXiv  Detail & Related papers  (2026-04-05T22:45:33Z)
• Reasoning with Confidence: Efficient Verification of LLM Reasoning Steps via Uncertainty Heads [104.9566359759396]
  We propose a lightweight alternative for step-level reasoning verification based on data-driven uncertainty scores.<n>Our findings suggest that the internal states of LLMs encode their uncertainty and can serve as reliable signals for reasoning verification.
  arXiv  Detail & Related papers  (2025-11-09T03:38:29Z)
• Your AI, Not Your View: The Bias of LLMs in Investment Analysis [62.388554963415906]
  In finance, Large Language Models (LLMs) face frequent knowledge conflicts arising from discrepancies between their pre-trained parametric knowledge and real-time market data.<n>These conflicts are especially problematic in real-world investment services, where a model's inherent biases can misalign with institutional objectives.<n>We propose an experimental framework to investigate emergent behaviors in such conflict scenarios, offering a quantitative analysis of bias in investment analysis.
  arXiv  Detail & Related papers  (2025-07-28T16:09:38Z)
• UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making [47.64013151246807]
  Large Language Models (LLMs) are integrated into safety-critical applications involving sequential decision-making.<n>Existing LLM Uncertainty Quantification (UQ) methods are primarily designed for single-turn question-answering formats.<n>We introduce a principled, information-theoretic framework that decomposes LLM sequential decision uncertainty into two parts.
  arXiv  Detail & Related papers  (2025-06-20T18:34:04Z)
• LLM-Enhanced Black-Litterman Portfolio Optimization [30.37210534945387]
  This study proposes and validates a systematic frame- work that translates return forecasts and predictive uncertainty from Large Language Models into the core inputs for the Black-Litterman model.<n>Through a backtest on S&P 500 constituents, we demonstrate that portfolios driven by top-performing LLMs significantly out- perform traditional baselines in both absolute and risk-adjusted terms.
  arXiv  Detail & Related papers  (2025-04-19T16:26:14Z)
• Exposing Product Bias in LLM Investment Recommendation [35.192944979712394]
  Large language models (LLMs), as a new generation of recommendation engines, possess powerful summarization and data analysis capabilities.<n>In this paper, we reveal a novel product bias in LLM investment recommendation, where LLMs exhibit systematic preferences for specific products.<n>Such preferences can subtly influence user investment decisions, potentially leading to inflated valuations of products and financial bubbles.
  arXiv  Detail & Related papers  (2025-03-11T13:10:00Z)
• ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks [91.55895047448249]
  This paper presents ReEval, an LLM-based framework using prompt chaining to perturb the original evidence for generating new test cases. We implement ReEval using ChatGPT and evaluate the resulting variants of two popular open-domain QA datasets. Our generated data is human-readable and useful to trigger hallucination in large language models.
  arXiv  Detail & Related papers  (2023-10-19T06:37:32Z)
• Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection [74.51523859064802]
  We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) Self-RAG enhances an LM's quality and factuality through retrieval and self-reflection. It significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-10-17T18:18:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.