发表机构
Hankuk University of Foreign Studies; UNIST; LG AI Research; Hanwha Life; University of Florida; Massachusetts Institute of Technology; LinqAlpha（韩国外国语大学; 蔚山科学技术院; LG AI研究院; 韩华生命保险; 佛罗里达大学; 麻省理工学院; LinqAlpha）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出投资偏差旋钮这一推理时单个神经元干预方法，可在不修改提示或参数的情况下，稳定校准LLM的整体投资立场，且适用于不同场景。
AI 中文摘要
大语言模型（LLMs）越来越多地被用于投资决策，但现有研究表明它们存在系统性的、模型特有的投资偏好。我们研究是否可以将模型的整体投资立场校准到指定的方向和强度。我们提出了投资偏差旋钮（investment-bias dial），这是一种对单个神经元的推理时干预方法，可连续调整模型级别的决策先验——即模型整体的买卖倾向，且不针对特定公司或投资属性。我们使用匹配的正负证据评估了五个开放权重的LLMs，发现该旋钮可在不修改提示或模型参数的情况下，使投资立场产生单调变化。在响应层面，该旋钮在相同输入下既改变投资决策，也改变生成理由的证据权重；在智能体检索环境中，它还会改变模型搜索的信息、选择的证据以及最终分析中体现的证据；在长上下文评估中，随着上下文长度增加，该旋钮可保持稳定的立场控制，而匹配的系统提示指令则会逐渐减弱。我们还在探索性回测中表明，旋钮的变化会传导至证券排名和下游投资组合构成。总体而言，我们的结果表明，LLM的总体投资立场可在推理时校准到指定目标。
英文摘要
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.
