AI financial advice is surprisingly good — especially if you ask the right questions

People are increasingly turning to artificial intelligence for financial advice, but will following it improve their financial standing?人们正越来越多地转向人工智能寻求财务建议，但听从这些建议真的能改善他们的财务状况吗？

“Half of Americans say they are using AI to get financial advice, but we know very little about what kind of advice they’re getting and whether they’re acting on it,” said Taha Choukhmane, an assistant professor of finance at the MIT Sloan School of Management and co-author of a new paper that measures and analyzes the quality of financial advice given by large language models.麻省理工学院斯隆管理学院金融学助理教授、一篇评估大型语言模型财务建议质量的新论文的合著者塔哈·舒赫曼（Taha Choukhmane）表示：“有一半的美国人称他们正在使用人工智能获取财务建议，但我们对他们究竟得到了什么样的建议以及是否采纳了这些建议知之甚少。”

Research by Choukhmane and co-authors showed that following AI recommendations can result in sizable saving buffers for virtually all individuals above age 30.舒赫曼及其合著者进行的研究表明，对于几乎所有30岁以上的人来说，遵循人工智能的建议可以带来可观的储蓄缓冲。

AI consistently advised people to save during their working years, draw down savings in retirement, invest heavily in diversified stock funds, and reduce stock exposure after age 45. However, AI chatbots were less successful in adjusting to shocks like unemployment, and they allowed portfolios to drift rather than actively rebalancing them.人工智能始终建议人们在工作期间储蓄，在退休后支取储蓄，大量投资于多元化的股票基金，并在45岁后降低股票敞口。然而，人工智能聊天机器人在应对失业等突发状况时表现欠佳，且倾向于让投资组合“漂移”，而非进行积极的再平衡。

The quality of financial advice given by LLMs improved when the researchers introduced more structured prompts, but the AI still often generated too little active portfolio rebalancing. 当研究人员引入更结构化的提示词（prompt）时，大型语言模型（LLM）提供的财务建议质量有所提高，但人工智能在主动调整投资组合方面仍显得不足。

How the study was conducted研究方法

The researchers built a model reflecting how people’s incomes, jobs, investments, and taxes typically evolve over their lives, which gave them a benchmark for what “good” financial decisions look like. 研究人员构建了一个模型，用以反映人们的收入、工作、投资和税收随生命周期的典型演变过程，从而为衡量“好的”财务决策提供了基准。

Then they asked a sample of 1,000 adults to write their own prompts seeking spending and investing advice from GPT-5.2, GPT-5.6, or Gemini 3 Flash. 随后，他们邀请了1000名成年人编写自己的提示词，向GPT-5.2、GPT-5.6或Gemini 3 Flash寻求消费和投资建议。

Next, they simulated what would happen if people from 22 to 89 years of age followed that advice over time, repeatedly asking AI these same types of questions and following its advice on spending, saving, and investing. 接下来，他们模拟了22岁至89岁的人群在一段时间内遵循这些建议的情况，即反复向人工智能提出同样类型的问题，并按照其在消费、储蓄和投资方面的建议行事。

Finally, they repeated the exercise using well-written academic prompts that included full financial information and clear assumptions. These more-detailed prompts included information on the individual’s age, job status, income, and savings balances, along with assumptions about the economic environment. 最后，他们使用包含完整财务信息和明确假设的专业学术提示词重复了上述练习。这些更详细的提示词涵盖了个人的年龄、工作状态、收入和储蓄余额，以及对经济环境的假设。

The authors compared the simulated advice (what would happen if regular people followed the AI recommendations from the prompts they gave) to what people were already doing financially without the help of AI. They also compared the simulated advice to the academic prompt. 作者将模拟建议（即普通人遵循其给出的提示词所获得的人工智能建议）与人们在没有人工智能帮助下已经采取的财务行为进行了对比。他们还将模拟建议与学术提示词产生的建议进行了比较。

The results showed that LLMs can offer an affordable, widely accessible source of financial guidance that can help users overcome the significant costs, biases, and conflicts of interest associated with traditional human financial advisors.结果显示，大型语言模型可以提供一种负担得起且广泛可及的财务指导来源，帮助用户克服与传统人类财务顾问相关的巨额成本、偏见和利益冲突。

Breaking down the findings研究发现解析

Overall, the researchers found that the financial advice given by LLMs over time is good but gets better when the questions are asked in an academic fashion, and that the models have strengths and weaknesses. 总体而言，研究人员发现大型语言模型随时间推移提供的财务建议质量尚可，且在以学术方式提问时效果更佳，同时这些模型各具优劣。

1. AI encourages smart financial behavior.1. 人工智能鼓励明智的财务行为。

LLM advice was better than the scholars expected, regardless of whether the prompts were written by regular users or by academics. It steered people toward higher savings, increased participation in the stock market, and promoted well-diversified allocations and age-appropriate risk-taking. 无论提示词是由普通用户还是学者编写，大型语言模型的建议都比学者们预期的要好。它引导人们增加储蓄、提高股市参与度，并促进了多元化的资产配置和符合年龄的风险承担。

“We were somewhat surprised by how good the advice was,” Choukhmane said. “Especially when you read the kind of questions people asked, it was not a given that the advice would line up with what academics think are good financial principles.”“我们对建议的质量感到有些惊讶，”舒赫曼说，“特别是当你阅读人们提出的问题时，这些建议能与学术界公认的良好财务原则相符，这并非理所当然。”

2. AI misses important nuances. Better prompts could help.2. 人工智能忽略了重要细节。更好的提示词或许能有所帮助。

The LLMs’ advice fell short on more subtle aspects of good financial planning. It tended to rely on simple rules of thumb for saving and spending and didn’t adjust well enough when circumstances changed. For example, it advised people who had experienced a job loss to cut spending too sharply, even when they had savings. 大型语言模型的建议在良好财务规划的微妙之处上表现不足。它倾向于依赖简单的经验法则来处理储蓄和消费，且在环境变化时调整不够灵活。例如，它建议失业者过度削减开支，即使他们仍有储蓄。

The way people ask questions is part of the problem. A typical prompt might read: “Where should I invest starting with $50 and consistently adding $25 a month after?”人们提问的方式是问题的一部分。一个典型的提示词可能是：“我应该如何投资？初始资金50美元，之后每月固定增加25美元？”

When a more detailed, structured “academic” prompt was used, the LLM performed better. For example, an academic prompt might tell the chatbot to assume normal life expectancy, living expenditures, retirement age, employment risk, and income risk, and to assume that current U.S. tax law and Social Security rules will not change.当使用更详细、结构化的“学术型”提示词时，大型语言模型的表现更好。例如，学术型提示词可能会要求聊天机器人假设正常预期寿命、生活支出、退休年龄、就业风险和收入风险，并假设当前的美国税法和社会保障规则不会改变。

“Regular people are not writing their prompts the way a finance professor is,” Choukhmane said.“普通人编写提示词的方式与金融学教授不同，”舒赫曼说。

3. AI advice varies depending on the user, which can lead to wealth gaps.3. 人工智能的建议因用户而异，这可能导致财富差距。

The authors found that LLMs’ advice differs depending on the prompter’s gender, financial literacy, and experience, leading to meaningful gaps in retirement wealth. 作者发现，大型语言模型的建议会根据提问者的性别、金融素养和经验而有所不同，从而导致退休财富出现显著差距。

Following the advice in response to prompts written by men, more financially literate users, or those with prior AI experience generated about 5% more wealth close to retirement. Specifically, 遵循由男性、金融素养较高者或有AI使用经验者所写提示词而得到的建议，在临近退休时产生的财富多出约5%。具体表现为：

• The LLM recommended higher equity allocations in response to prompts written by men and by individuals with high financial literacy. Over the life cycle, such differences in investment advice compounded into roughly $50,000 (4%) lower wealth at age 60 for women and for less financially literate users.针对男性和金融素养较高者编写的提示词，大型语言模型建议了更高的股票配置比例。在整个生命周期中，这种投资建议的差异导致女性和金融素养较低者的60岁财富水平降低了约5万美元（4%）。
• The LLM recommended lower saving rates in response to prompts written by individuals who had not previously used AI for financial advice. Following the advice left them with almost $100,000 (6%) less wealth at age 60 than individuals with prior AI experience. 针对此前未使用过人工智能进行财务咨询的人编写的提示词，大型语言模型建议了较低的储蓄率。遵循这些建议使他们在60岁时的财富比有AI使用经验的人少了近10万美元（6%）。

These differences come from two sources, Choukhmane said. First, different users asked different kinds of questions and often brought up different topics. Women, for example, were more likely to use words such as “family,” “grocery,” and “pay” in their prompts, while men used words like “strategy,” “crypto,” and “growth,” he said. 舒赫曼指出，这些差异来自两个方面。首先，不同用户提出的问题类型不同，涉及的话题也不同。例如，女性在提示词中更倾向于使用“家庭”、“杂货”和“支付”等词汇，而男性则使用“策略”、“加密货币”和“增长”等词汇。

Artificial Intelligence for Financial Services人工智能在金融服务中的应用

In person at MIT Sloan麻省理工学院斯隆管理学院线下活动

Register Now立即注册

Second, the model may give different advice even when the underlying question is the same. In the case of gender, about two-thirds of the gender gap in wealth outcomes could be attributed to differences in how men and women wrote their prompts, while the remaining third came from the model changing its advice when the same prompt was labeled as coming from a woman rather than a man. 其次，即使基本问题相同，模型也可能给出不同的建议。以性别为例，财富结果中约三分之二的性别差距可归因于男女编写提示词方式的差异，而其余三分之一则源于当同一个提示词被标记为女性而非男性时，模型改变了其建议。

That latter pattern could reflect the LLM making reasonable inferences about how preferences or circumstances vary by gender — which, ideally, the model could make explicit to users, Choukhmane said — or it could reflect biases learned from training data.舒赫曼表示，后一种模式可能反映了大型语言模型对不同性别偏好或情况差异所做的合理推断（理想情况下，模型应向用户明确这一点），也可能反映了从训练数据中学到的偏见。

The challenge with AI financial advice is that there are no clear benchmarks, Choukhmane said. Only when there is an accepted framework for how advice should vary with demographics will LLMs be capable of progressing in the right direction. He said he remains hopeful that will happen. 舒赫曼认为，人工智能财务建议面临的挑战在于缺乏明确的基准。只有当关于建议应如何随人口统计学特征而变化的框架被广泛接受时，大型语言模型才能朝着正确的方向进步。他表示对此持乐观态度。

In addition, it’s important to remember that not all variation in advice is problematic, Choukhmane said. For example, “we want [the LLM] to have different bias because men and women are different and have different life expectancy and income risk,” he said. 此外，舒赫曼提醒，并非所有建议的差异都是有问题的。例如，“我们希望（大型语言模型）有不同的偏见，因为男女确实不同，且预期寿命和收入风险也各不相同，”他说。

Takeaways for consumers 给消费者的建议

Beyond being mindful of bias, and, for the time being, asking LLMs to guard against it, success boils down to smarter prompts. Prompts grounded in life-cycle planning, portfolio theory, and real-world financial assumptions improved advice on spending and saving and cut down on basic, rule-of-thumb answers.除了关注偏见并在现阶段要求人工智能防范偏见外，成功的关键在于更智能的提示词。基于生命周期规划、投资组合理论和现实财务假设的提示词，能改善消费和储蓄建议，并减少基础的、经验法则式的回答。

“I think the real challenge is, how do we make sure that AI financial advice delivers for people who don’t have [a] level of financial literacy and who don’t write prompts perfectly?” Choukhmane said. One idea for people interested in using AI for financial advice is to start by using AI as a tool for building financial understanding rather than simply following its advice.“我认为真正的挑战在于，如何确保人工智能财务建议能为那些金融素养水平不高、无法完美编写提示词的人提供服务？”舒赫曼说。对于有兴趣使用人工智能获取财务建议的人，一个建议是：将其作为构建财务认知的工具，而不是盲目遵循其建议。

AI can serve as a good complement to working with a financial advisor — someone you might meet with twice a year — because it can help you implement the advice they give you in real time, Choukhmane said. 舒赫曼表示，人工智能可以作为人类财务顾问（可能一年只见两次面）的良好补充，因为它可以帮助用户实时执行顾问提供的建议。

And for people who don’t have the money to work with a human financial advisor, AI is a good way to get advice inexpensively. “A lot of the people who would benefit from financial advice are precisely the people who don’t have a lot of resources,” he said.对于没有资金聘请人类财务顾问的人来说，人工智能是一种低成本获取建议的好方法。“许多能从财务建议中获益的人，恰恰是那些资源匮乏的人，”他说。

Takeaways for business 给企业的建议

As consumers increasingly turn to LLMs for financial advice, providers may need to rethink how customers learn about their products. The study found that LLMs often recommended specific account types, financial products, and providers that respondents themselves did not mention. (For example, Vanguard investment products appeared in 6% of LLM responses, and iShares products appeared in 3.4%, even though fewer than 0.4% of prompts mentioned either company.)随着消费者越来越多地转向大型语言模型寻求财务建议，服务提供商可能需要重新思考客户了解其产品的方式。研究发现，大型语言模型经常推荐受访者本人并未提及的特定账户类型、金融产品和提供商。（例如，Vanguard投资产品出现在6%的人工智能回复中，iShares产品出现在3.4%中，尽管只有不到0.4%的提示词提到了这两家公司。）

That suggests that AI advice might be changing how people find and compare financial products, Choukhmane said. For financial firms, attracting customers’ attention may depend less on traditional marketing or search visibility and more on whether and how their products are described by LLMs when consumers seek advice.舒赫曼表示，这表明人工智能的建议可能会改变人们发现和比较金融产品的方式。对于金融公司而言，吸引客户的注意力可能不再仅依赖传统的营销或搜索可见度，而更多取决于消费者寻求建议时，大型语言模型如何描述其产品。

“AI Financial Advice: Supply, Demand, and Life Cycle Implications,” which won the Swiss Finance Institute Outstanding Paper Award 2026, was written by Taha Choukhmane, Weidong Lin, and Matthew Akuzawa from MIT Sloan and by Tim de Silva from the Stanford Graduate School of Business.《人工智能财务建议：供给、需求与生命周期影响》（AI Financial Advice: Supply, Demand, and Life Cycle Implications）荣获2026年瑞士金融研究所杰出论文奖，由麻省理工学院斯隆管理学院的塔哈·舒赫曼、林卫东（Weidong Lin）、马修·阿库扎瓦（Matthew Akuzawa）以及斯坦福大学商学院的蒂姆·德·席尔瓦（Tim de Silva）共同撰写。

Taha Choukhmane is an assistant professor of finance at the MIT Sloan School of Management. Choukhmane received the 2025 TIAA Paul A. Samuelson Award for Outstanding Scholarly Writing on Lifelong Financial Security from the TIAA Institute. His winning paper, co-authored with Lucas Goodman of the U.S. Department of the Treasury and Yale University’s Cormac O’Dea, is “Efficiency in Household Decision-Making: Evidence From the Retirement Savings of US Couples.”塔哈·舒赫曼是麻省理工学院斯隆管理学院金融学助理教授。舒赫曼获得了TIAA研究所颁发的2025年TIAA保罗·萨缪尔森终身财务保障杰出学术著作奖。他的获奖论文《家庭决策的效率：来自美国夫妇退休储蓄的证据》（Efficiency in Household Decision-Making: Evidence From the Retirement Savings of US Couples）与美国财政部的卢卡斯·古德曼（Lucas Goodman）及耶鲁大学的科马克·奥迪亚（Cormac O’Dea）合著。