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

arXiv: https://arxiv.org/abs/2602.16990 · HTML: https://mlsanity.com/paper/2602.16990/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 47 references that are in the map.
- First posted on arXiv 19 Feb 2026.

## Builds on (most cited first, 17 of 17)

- [Uncovering ChatGPT's Capabilities in Recommender Systems](https://mlsanity.com/paper/2305.02182/) (2023)
- [Advances and Challenges in Conversational Recommender Systems: A Survey](https://mlsanity.com/paper/2101.09459/) (2021)
- [Conversational Recommender System](https://mlsanity.com/paper/1806.03277/) (2018)
- [LLM-Rec: Personalized Recommendation via Prompting Large Language Models](https://mlsanity.com/paper/2307.15780/) (2023)
- [INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent](https://mlsanity.com/paper/2412.18174/) (2024)
- [DocMath-Eval: Evaluating Math Reasoning Capabilities of LLMs in Understanding Long and Specialized Documents](https://mlsanity.com/paper/2311.09805/) (2023)
- [Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance](https://mlsanity.com/paper/2502.08127/) (2025)
- [Data-Driven Estimation in Equilibrium Using Inverse Optimization](https://mlsanity.com/paper/1308.3397/) (2013)
- [Evaluating ChatGPT as a Recommender System: A Rigorous Approach](https://mlsanity.com/paper/2309.03613/) (2023)
- [Are Generative AI Agents Effective Personalized Financial Advisors?](https://mlsanity.com/paper/2504.05862/) (2025)
- [UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations](https://mlsanity.com/paper/2507.07030/) (2025)
- [FairEval: Evaluating Fairness in LLM-Based Recommendations with Personality Awareness](https://mlsanity.com/paper/2504.07801/) (2025)
- [Personality-Driven Social Multimedia Content Recommendation](https://mlsanity.com/paper/2207.12236/) (2022)
- [FAR-Trans: An Investment Dataset for Financial Asset Recommendation](https://mlsanity.com/paper/2407.08692/) (2024)
- [FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information](https://mlsanity.com/paper/2505.20650/) (2025)
- [PerFairX: Is There a Balance Between Fairness and Personality in Large Language Model Recommendations?](https://mlsanity.com/paper/2509.08829/) (2025)
- [StockBabble: A Conversational Financial Agent to support Stock Market Investors](https://mlsanity.com/paper/2106.08298/) (2021)

## Built on by (most cited first, 4 of 4)

- [Sell Me This Stock: Unsafe Recommendation Drift in LLM Agents](https://mlsanity.com/paper/2603.12564/) (2026)
- [Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models](https://mlsanity.com/paper/2604.24608/) (2026)
- [Are LLMs Good Financial User Simulators? Multi-view Investor Logic Alignment (MILA)](https://mlsanity.com/paper/2609.15727/) (2026)
- [BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents](https://mlsanity.com/paper/2610.06748/) (2026)

## Abstract (arXiv)

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.