One Size Fits None: Heuristic Collapse in LLM Investment Advice

arXiv:2604.23837v1 Announce Type: new Abstract: Large language models are increasingly deployed as advisors in high-stakes domains -- answering medical questions, interpreting legal documents, recommending financial products -- where good advice requires integrating a user's full context rather than responding to salient surface features. We investigate whether frontier LLMs actually do this, or whether they instead exhibit heuristic collapse: a systematic reduction of complex, multi-factor decisions to a small number of dominant inputs. We study the phenomenon in investment advice, where legal standards explicitly require individualized reasoning over a client's full circumstances. Applying interpretable surrogate models to LLM outputs, we find systematic heuristic collapse: investment allocation decisions are largely determined by self-reported risk tolerance, while other relevant factors contribute minimally. We further find that web search partially attenuates heuristic collapse but does not resolve it. These findings suggest that heuristic collapse is not resolved by web search augmentation or model scale alone, and that deploying LLMs as advisors requires auditing input sensitivity, not just output quality.

Related

• Calibrated? Not for Everyone: How Sexual Orientation and Religious Markers Distort LLM Accuracy and Confidence in Medical QA
• Why Don't You Know? Evaluating the Impact of Uncertainty Sources on Uncertainty Quantification in LLMs
• Stop Listening to Me! How Multi-turn Conversations Can Degrade LLM Diagnostic Reasoning
• Before the First Token: Scale-Dependent Emergence of Hallucination Signals in Autoregressive Language Models

Source: arXiv cs.CL | 2026-04-28