Conv-FinRe: A Conversational and Longitudinal Benchmark for Utility-Grounded Financial Recommendation

TL;DR

Conv-FinRe introduces a novel benchmark for financial recommendation that evaluates large language models on decision quality and behavioral alignment using real market data and advisory dialogues.

Contribution

It presents a new conversational and longitudinal benchmark that distinguishes normative utility from descriptive behavior in financial recommendations.

Findings

Models with high utility ranking often diverge from user choices.

Behaviorally aligned models tend to overfit short-term noise.

The benchmark reveals a tension between rational decision-making and mimicking user behavior.

Abstract

Most recommendation benchmarks evaluate how well a model imitates user behavior. In financial advisory, however, observed actions can be noisy or short-sighted under market volatility and may conflict with a user's long-term goals. Treating what users chose as the sole ground truth, therefore, conflates behavioral imitation with decision quality. We introduce Conv-FinRe, a conversational and longitudinal benchmark for stock recommendation that evaluates LLMs beyond behavior matching. Given an onboarding interview, step-wise market context, and advisory dialogues, models must generate rankings over a fixed investment horizon. Crucially, Conv-FinRe provides multi-view references that distinguish descriptive behavior from normative utility grounded in investor-specific risk preferences, enabling diagnosis of whether an LLM follows rational analysis, mimics user noise, or is driven by market momentum. We build the benchmark from real market data and human decision trajectories, instantiate controlled advisory conversations, and evaluate a suite of state-of-the-art LLMs. Results reveal a persistent tension between rational decision quality and behavioral alignment: models that perform well on utility-based ranking often fail to match user choices, whereas behaviorally aligned models can overfit short-term noise. The dataset is publicly released on Hugging Face, and the codebase is available on GitHub.