{"id":231190,"date":"2025-09-25T10:40:48","date_gmt":"2025-09-25T14:40:48","guid":{"rendered":"https:\/\/ibkrcampus.com\/campus\/?p=231190"},"modified":"2025-09-26T08:30:37","modified_gmt":"2025-09-26T12:30:37","slug":"when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks","status":"publish","type":"post","link":"https:\/\/www.interactivebrokers.com\/campus\/ibkr-quant-news\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\/","title":{"rendered":"When LLMs Go Abroad: Why U.S. AI Models Are Too Optimistic on Chinese Stocks"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\"><em>The article &#8220;When LLMs Go Abroad: Why U.S. AI Models Are Too Optimistic on Chinese Stocks&#8221; was originally published on <a href=\"https:\/\/alphaarchitect.com\/ai-models\/\">Alpha Architect<\/a> blog. <\/em><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Large language models are increasingly being used to forecast stock prices and guide investment decisions. But what happens when these models cross borders? This paper shows that U.S.-based LLMs, like ChatGPT, systematically produce more optimistic forecasts for Chinese firms than Chinese-based models. The bias isn\u2019t about fundamentals \u2013 it stems from asymmetries in media coverage and training data. By unpacking this \u201cforeign bias,\u201d the authors highlight a new source of risk for global investors: AI models may amplify information gaps rather than close them.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">We\u2019ve previously seen research on how AI stacks up against human analysts in stock return prediction \u2014 see&nbsp;<a href=\"https:\/\/alphaarchitect.com\/stock-analysis\/\" target=\"_blank\" rel=\"noreferrer noopener\">Stock analysis: How does AI perform vs. humans?<\/a>. The current paper complements that by showing how AI\u2019s predictions also vary depending on geography and media exposure.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"h-when-llms-go-abroad-foreign-bias-in-ai-financial-predictions\">When LLMs Go Abroad: Foreign Bias in AI Financial Predictions<\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Cao, Wang, Yi<\/li>\n\n\n\n<li>Harvard working paper, 2025<\/li>\n\n\n\n<li>A version of this paper can be found&nbsp;<a href=\"https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=5440116\" target=\"_blank\" rel=\"noreferrer noopener\">here<\/a><\/li>\n\n\n\n<li>Want to read our summaries of academic finance papers? Check out our&nbsp;<a href=\"https:\/\/alphaarchitect.com\/category\/architect-academic-insights\/academic-research-insight\/\" target=\"_blank\" rel=\"noreferrer noopener\">Academic Research Insight<\/a>&nbsp;category<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"h-key-academic-insights\">Key Academic Insights<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>US-LLMs Show Optimism toward Foreign Firms<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">When comparing ChatGPT (US-based) vs DeepSeek (China-based), the authors find that ChatGPT gives&nbsp;<em>higher end-of-year price predictions<\/em>&nbsp;and more \u201cbuy\u201d recommendations for Chinese firms. This is unexpected- because usually the \u201chome bias\u201d means domestic assets are favored. Here, we see almost the opposite in the AI realm.<\/p>\n\n\n\n<h4 class=\"wp-block-heading\" id=\"h-bias-tied-to-asymmetric-media-exposure\">Bias Tied to Asymmetric Media Exposure<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">The bias appears strongest when U.S media&nbsp;<em>silences negative news<\/em>&nbsp;about Chinese firms, while Chinese media covers them more fully. When ChatGPT sees less negative coverage from U.S. sources, it remains optimistic. The reverse asymmetry is a key mechanism.<\/p>\n\n\n\n<h4 class=\"wp-block-heading\" id=\"h-synthetic-control-amp-prompting-show-missing-data-is-key\">Synthetic Control &amp; Prompting Show Missing Data Is Key<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">The authors construct placebo firms with synthetic data: ones where media coverage is balanced. For those, the optimism gap between ChatGPT and DeepSeek disappears. Also, when you&nbsp;<em>prompt ChatGPT<\/em>&nbsp;with Chinese-media negative news (even though you can\u2019t change its internal weights), the bias vanishes. That tells us the issue is missing or skewed training data, not model architecture per se.<\/p>\n\n\n\n<h4 class=\"wp-block-heading\" id=\"h-diverging-forecasts-may-worsen-global-information-asymmetry\">Diverging Forecasts May Worsen Global Information Asymmetry<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">Because different countries\u2019 LLMs pick up different biases in training data, financial forecasts for the same firm may diverge depending on which model or language domain is used. That means AI might&nbsp;<em>amplify<\/em>&nbsp;rather than close information gaps between investors in different jurisdictions.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"h-practical-applications-for-investment-advisors\">Practical Applications for Investment Advisors<\/h2>\n\n\n\n<ol class=\"wp-block-list\">\n<li>Before relying on LLM forecasts, especially cross-border, check&nbsp;<em>which model<\/em>&nbsp;is used, and what datasets it has been exposed to. A U.S-model may miss negative local coverage; local models may have biases of their own.<\/li>\n\n\n\n<li>Use prompts or supplement sources: if a U.S-LLM seems overly rosy about a foreign firm, include local news sources (negative and positive) in your prompt to counteract possible missing data effects.<\/li>\n\n\n\n<li>Diversify model sources: cross-validate predictions from an LLM trained in the target country (or language) to see if there are systematic discrepancies.<\/li>\n\n\n\n<li>Regulatory and compliance teams should demand transparency about LLM training data, so investors\/clients understand what \u201cnews exposure\u201d the model had\u2014or lacked.<\/li>\n<\/ol>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"h-how-to-explain-this-to-clients\">How to Explain This to Clients<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">\u201cImagine two reporters covering the same company. One works in New York, sees mostly rosy headlines, or perhaps doesn\u2019t get access to the critical local press. The other stays in the company\u2019s home country, sees both praise and negative criticism. Their stories will be different. LLMs are like those reporters. If the U.S. model saw less critical Chinese media, it tends to give you a sunnier view of Chinese firms than the China-based model. That doesn\u2019t mean the firm is doing better\u2014it just means the model saw less bad stuff. So use multiple \u2018eyes\u2019 to judge.\u201d<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"h-the-most-important-chart-from-the-paper\">The Most Important Chart from the Paper<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>TABLE 2: ChatGPT vs. DeepSeek: Price Predictions and Stock Recommendations<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">This chart plots the difference between ChatGPT\u2019s predicted end-of-year stock price (or \u201cbuy\u201d recommendation rate) vs DeepSeek\u2019s, across Chinese firms. It shows that when U.S. media coverage of negative events is lower (relative to Chinese media), this gap widens significantly. Once negative Chinese news is added to prompts, the gap collapses almost fully.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img decoding=\"async\" width=\"800\" height=\"627\" data-src=\"https:\/\/www.interactivebrokers.com\/campus\/wp-content\/uploads\/sites\/2\/2025\/09\/AI-Models-Chinese-Stocks.png\" alt=\"AI Models Are Too Optimistic on Chinese Stocks\" class=\"wp-image-231194 lazyload\" data-srcset=\"https:\/\/ibkrcampus.com\/campus\/wp-content\/uploads\/sites\/2\/2025\/09\/AI-Models-Chinese-Stocks.png 800w, https:\/\/ibkrcampus.com\/campus\/wp-content\/uploads\/sites\/2\/2025\/09\/AI-Models-Chinese-Stocks-700x549.png 700w, https:\/\/ibkrcampus.com\/campus\/wp-content\/uploads\/sites\/2\/2025\/09\/AI-Models-Chinese-Stocks-300x235.png 300w, https:\/\/ibkrcampus.com\/campus\/wp-content\/uploads\/sites\/2\/2025\/09\/AI-Models-Chinese-Stocks-768x602.png 768w\" data-sizes=\"(max-width: 800px) 100vw, 800px\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" style=\"--smush-placeholder-width: 800px; aspect-ratio: 800\/627;\" \/><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\"><em>The results are hypothetical results and are NOT an indicator of future results and do NOT represent returns that any investor actually attained.&nbsp;Indexes are unmanaged and do not reflect management or trading fees, and one cannot invest directly in an index<\/em>.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Abstract<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">We document foreign biases in AI-generated financial predictions: ChatGPT (US-based) is systematically more optimistic about Chinese firms than DeepSeek (China-based), predicting higher end-of-year stock prices and generating more buy recommendations. This AI-specific phenomenon contradicts the traditional home bias in which investors favor domestic assets. We trace this bias to differential information access: ChatGPT\u2019s optimism increases when US media coverage of Chinese firms\u2019 negative news is scarce relative to Chinese media. Supporting this mechanism, placebo tests with synthetic Chinese firms without such asymmetries show no prediction gap between models. Crucially, providing ChatGPT with Chinese news through prompts-which cannot alter model weights-completely eliminates the prediction gap, demonstrating that the bias stems from missing training data. Our findings imply that the parallel development of LLMs in different countries can create divergent financial forecasts, potentially amplifying rather than reducing cross-border information asymmetries as these tools shape investment decisions globally.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>This paper shows that U.S.-based LLMs, like ChatGPT, systematically produce more optimistic forecasts for Chinese firms than Chinese-based models. <\/p>\n","protected":false},"author":152,"featured_media":225517,"comment_status":"open","ping_status":"closed","sticky":true,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":"","jetpack_post_was_ever_published":false},"categories":[339,338,341],"tags":[632,14403,18427,1006,17952],"contributors-categories":[13651],"class_list":["post-231190","post","type-post","status-publish","format-standard","has-post-thumbnail","category-data-science","category-ibkr-quant-news","category-quant-development","tag-ai","tag-chatgpt","tag-deepseek","tag-fintech","tag-large-language-models-llms","contributors-categories-alpha-architect"],"pp_statuses_selecting_workflow":false,"pp_workflow_action":"current","pp_status_selection":"publish","acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v26.9 (Yoast SEO v28.2) - https:\/\/yoast.com\/product\/yoast-seo-premium-wordpress\/ -->\n<title>When LLMs Go Abroad: Why U.S. AI Models Are Too Optimistic on Chinese Stocks<\/title>\n<meta name=\"description\" content=\"This paper shows that U.S.-based LLMs, like ChatGPT, systematically produce more optimistic forecasts for Chinese firms than Chinese-based models.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.interactivebrokers.com\/campus\/wp-json\/wp\/v2\/posts\/231190\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"When LLMs Go Abroad: Why U.S. AI Models Are Too Optimistic on Chinese Stocks\" \/>\n<meta property=\"og:description\" content=\"This paper shows that U.S.-based LLMs, like ChatGPT, systematically produce more optimistic forecasts for Chinese firms than Chinese-based models.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.interactivebrokers.com\/campus\/ibkr-quant-news\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\/\" \/>\n<meta property=\"og:site_name\" content=\"IBKR Campus US\" \/>\n<meta property=\"article:published_time\" content=\"2025-09-25T14:40:48+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-09-26T12:30:37+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.interactivebrokers.com\/campus\/wp-content\/uploads\/sites\/2\/2025\/06\/tech-ai-featured-img.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"563\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Elisabetta Basilico, Ph.D., CFA\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Elisabetta Basilico, Ph.D., CFA\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\n\t    \"@context\": \"https:\\\/\\\/schema.org\",\n\t    \"@graph\": [\n\t        {\n\t            \"@type\": \"NewsArticle\",\n\t            \"@id\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/ibkr-quant-news\\\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\\\/#article\",\n\t            \"isPartOf\": {\n\t                \"@id\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/ibkr-quant-news\\\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\\\/\"\n\t            },\n\t            \"author\": {\n\t                \"name\": \"Elisabetta Basilico, Ph.D., CFA\",\n\t                \"@id\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/#\\\/schema\\\/person\\\/be0fc850f28388c089a16534ce09be74\"\n\t            },\n\t            \"headline\": \"When LLMs Go Abroad: Why U.S. AI Models Are Too Optimistic on Chinese Stocks\",\n\t            \"datePublished\": \"2025-09-25T14:40:48+00:00\",\n\t            \"dateModified\": \"2025-09-26T12:30:37+00:00\",\n\t            \"mainEntityOfPage\": {\n\t                \"@id\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/ibkr-quant-news\\\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\\\/\"\n\t            },\n\t            \"wordCount\": 935,\n\t            \"commentCount\": 0,\n\t            \"publisher\": {\n\t                \"@id\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/#organization\"\n\t            },\n\t            \"image\": {\n\t                \"@id\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/ibkr-quant-news\\\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\\\/#primaryimage\"\n\t            },\n\t            \"thumbnailUrl\": \"https:\\\/\\\/www.interactivebrokers.com\\\/campus\\\/wp-content\\\/uploads\\\/sites\\\/2\\\/2025\\\/06\\\/tech-ai-featured-img.jpg\",\n\t            \"keywords\": [\n\t                \"AI\",\n\t                \"ChatGPT\",\n\t                \"DeepSeek\",\n\t                \"fintech\",\n\t                \"Large Language Models (LLMs)\"\n\t            ],\n\t            \"articleSection\": [\n\t                \"Data Science\",\n\t                \"Quant\",\n\t                \"Quant Development\"\n\t            ],\n\t            \"inLanguage\": \"en-US\",\n\t            \"potentialAction\": [\n\t                {\n\t                    \"@type\": \"CommentAction\",\n\t                    \"name\": \"Comment\",\n\t                    \"target\": [\n\t                        \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/ibkr-quant-news\\\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\\\/#respond\"\n\t                    ]\n\t                }\n\t            ]\n\t        },\n\t        {\n\t            \"@type\": \"WebPage\",\n\t            \"@id\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/ibkr-quant-news\\\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\\\/\",\n\t            \"url\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/ibkr-quant-news\\\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\\\/\",\n\t            \"name\": \"When LLMs Go Abroad: Why U.S. AI Models Are Too Optimistic on Chinese Stocks | IBKR Campus US\",\n\t            \"isPartOf\": {\n\t                \"@id\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/#website\"\n\t            },\n\t            \"primaryImageOfPage\": {\n\t                \"@id\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/ibkr-quant-news\\\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\\\/#primaryimage\"\n\t            },\n\t            \"image\": {\n\t                \"@id\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/ibkr-quant-news\\\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\\\/#primaryimage\"\n\t            },\n\t            \"thumbnailUrl\": \"https:\\\/\\\/www.interactivebrokers.com\\\/campus\\\/wp-content\\\/uploads\\\/sites\\\/2\\\/2025\\\/06\\\/tech-ai-featured-img.jpg\",\n\t            \"datePublished\": \"2025-09-25T14:40:48+00:00\",\n\t            \"dateModified\": \"2025-09-26T12:30:37+00:00\",\n\t            \"description\": \"This paper shows that U.S.-based LLMs, like ChatGPT, systematically produce more optimistic forecasts for Chinese firms than Chinese-based models.\",\n\t            \"inLanguage\": \"en-US\",\n\t            \"potentialAction\": [\n\t                {\n\t                    \"@type\": \"ReadAction\",\n\t                    \"target\": [\n\t                        \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/ibkr-quant-news\\\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\\\/\"\n\t                    ]\n\t                }\n\t            ]\n\t        },\n\t        {\n\t            \"@type\": \"ImageObject\",\n\t            \"inLanguage\": \"en-US\",\n\t            \"@id\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/ibkr-quant-news\\\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\\\/#primaryimage\",\n\t            \"url\": \"https:\\\/\\\/www.interactivebrokers.com\\\/campus\\\/wp-content\\\/uploads\\\/sites\\\/2\\\/2025\\\/06\\\/tech-ai-featured-img.jpg\",\n\t            \"contentUrl\": \"https:\\\/\\\/www.interactivebrokers.com\\\/campus\\\/wp-content\\\/uploads\\\/sites\\\/2\\\/2025\\\/06\\\/tech-ai-featured-img.jpg\",\n\t            \"width\": 1000,\n\t            \"height\": 563\n\t        },\n\t        {\n\t            \"@type\": \"WebSite\",\n\t            \"@id\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/#website\",\n\t            \"url\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/\",\n\t            \"name\": \"IBKR Campus US\",\n\t            \"description\": \"Financial Education from Interactive Brokers\",\n\t            \"publisher\": {\n\t                \"@id\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/#organization\"\n\t            },\n\t            \"potentialAction\": [\n\t                {\n\t                    \"@type\": \"SearchAction\",\n\t                    \"target\": {\n\t                        \"@type\": \"EntryPoint\",\n\t                        \"urlTemplate\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/?s={search_term_string}\"\n\t                    },\n\t                    \"query-input\": {\n\t                        \"@type\": \"PropertyValueSpecification\",\n\t                        \"valueRequired\": true,\n\t                        \"valueName\": \"search_term_string\"\n\t                    }\n\t                }\n\t            ],\n\t            \"inLanguage\": \"en-US\"\n\t        },\n\t        {\n\t            \"@type\": \"Organization\",\n\t            \"@id\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/#organization\",\n\t            \"name\": \"Interactive Brokers\",\n\t            \"alternateName\": \"IBKR\",\n\t            \"url\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/\",\n\t            \"logo\": {\n\t                \"@type\": \"ImageObject\",\n\t                \"inLanguage\": \"en-US\",\n\t                \"@id\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/#\\\/schema\\\/logo\\\/image\\\/\",\n\t                \"url\": \"https:\\\/\\\/www.interactivebrokers.com\\\/campus\\\/wp-content\\\/uploads\\\/sites\\\/2\\\/2024\\\/05\\\/ibkr-campus-logo.jpg\",\n\t                \"contentUrl\": \"https:\\\/\\\/www.interactivebrokers.com\\\/campus\\\/wp-content\\\/uploads\\\/sites\\\/2\\\/2024\\\/05\\\/ibkr-campus-logo.jpg\",\n\t                \"width\": 669,\n\t                \"height\": 669,\n\t                \"caption\": \"Interactive Brokers\"\n\t            },\n\t            \"image\": {\n\t                \"@id\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/#\\\/schema\\\/logo\\\/image\\\/\"\n\t            },\n\t            \"publishingPrinciples\": \"https:\\\/\\\/www.interactivebrokers.com\\\/campus\\\/about-ibkr-campus\\\/\",\n\t            \"ethicsPolicy\": \"https:\\\/\\\/www.interactivebrokers.com\\\/campus\\\/cyber-security-notice\\\/\"\n\t        },\n\t        {\n\t            \"@type\": \"Person\",\n\t            \"@id\": \"https:\\\/\\\/ibkrcampus.com\\\/campus\\\/#\\\/schema\\\/person\\\/be0fc850f28388c089a16534ce09be74\",\n\t            \"name\": \"Elisabetta Basilico, Ph.D., CFA\",\n\t            \"url\": \"https:\\\/\\\/www.interactivebrokers.com\\\/campus\\\/author\\\/elisabettabasilico\\\/\"\n\t        }\n\t    ]\n\t}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"When LLMs Go Abroad: Why U.S. AI Models Are Too Optimistic on Chinese Stocks","description":"This paper shows that U.S.-based LLMs, like ChatGPT, systematically produce more optimistic forecasts for Chinese firms than Chinese-based models.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.interactivebrokers.com\/campus\/wp-json\/wp\/v2\/posts\/231190\/","og_locale":"en_US","og_type":"article","og_title":"When LLMs Go Abroad: Why U.S. AI Models Are Too Optimistic on Chinese Stocks","og_description":"This paper shows that U.S.-based LLMs, like ChatGPT, systematically produce more optimistic forecasts for Chinese firms than Chinese-based models.","og_url":"https:\/\/www.interactivebrokers.com\/campus\/ibkr-quant-news\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\/","og_site_name":"IBKR Campus US","article_published_time":"2025-09-25T14:40:48+00:00","article_modified_time":"2025-09-26T12:30:37+00:00","og_image":[{"width":1000,"height":563,"url":"https:\/\/www.interactivebrokers.com\/campus\/wp-content\/uploads\/sites\/2\/2025\/06\/tech-ai-featured-img.jpg","type":"image\/jpeg"}],"author":"Elisabetta Basilico, Ph.D., CFA","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Elisabetta Basilico, Ph.D., CFA","Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/ibkrcampus.com\/campus\/ibkr-quant-news\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\/#article","isPartOf":{"@id":"https:\/\/ibkrcampus.com\/campus\/ibkr-quant-news\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\/"},"author":{"name":"Elisabetta Basilico, Ph.D., CFA","@id":"https:\/\/ibkrcampus.com\/campus\/#\/schema\/person\/be0fc850f28388c089a16534ce09be74"},"headline":"When LLMs Go Abroad: Why U.S. AI Models Are Too Optimistic on Chinese Stocks","datePublished":"2025-09-25T14:40:48+00:00","dateModified":"2025-09-26T12:30:37+00:00","mainEntityOfPage":{"@id":"https:\/\/ibkrcampus.com\/campus\/ibkr-quant-news\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\/"},"wordCount":935,"commentCount":0,"publisher":{"@id":"https:\/\/ibkrcampus.com\/campus\/#organization"},"image":{"@id":"https:\/\/ibkrcampus.com\/campus\/ibkr-quant-news\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\/#primaryimage"},"thumbnailUrl":"https:\/\/www.interactivebrokers.com\/campus\/wp-content\/uploads\/sites\/2\/2025\/06\/tech-ai-featured-img.jpg","keywords":["AI","ChatGPT","DeepSeek","fintech","Large Language Models (LLMs)"],"articleSection":["Data Science","Quant","Quant Development"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/ibkrcampus.com\/campus\/ibkr-quant-news\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/ibkrcampus.com\/campus\/ibkr-quant-news\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\/","url":"https:\/\/ibkrcampus.com\/campus\/ibkr-quant-news\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\/","name":"When LLMs Go Abroad: Why U.S. AI Models Are Too Optimistic on Chinese Stocks | IBKR Campus US","isPartOf":{"@id":"https:\/\/ibkrcampus.com\/campus\/#website"},"primaryImageOfPage":{"@id":"https:\/\/ibkrcampus.com\/campus\/ibkr-quant-news\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\/#primaryimage"},"image":{"@id":"https:\/\/ibkrcampus.com\/campus\/ibkr-quant-news\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\/#primaryimage"},"thumbnailUrl":"https:\/\/www.interactivebrokers.com\/campus\/wp-content\/uploads\/sites\/2\/2025\/06\/tech-ai-featured-img.jpg","datePublished":"2025-09-25T14:40:48+00:00","dateModified":"2025-09-26T12:30:37+00:00","description":"This paper shows that U.S.-based LLMs, like ChatGPT, systematically produce more optimistic forecasts for Chinese firms than Chinese-based models.","inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/ibkrcampus.com\/campus\/ibkr-quant-news\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/ibkrcampus.com\/campus\/ibkr-quant-news\/when-llms-go-abroad-why-u-s-ai-models-are-too-optimistic-on-chinese-stocks\/#primaryimage","url":"https:\/\/www.interactivebrokers.com\/campus\/wp-content\/uploads\/sites\/2\/2025\/06\/tech-ai-featured-img.jpg","contentUrl":"https:\/\/www.interactivebrokers.com\/campus\/wp-content\/uploads\/sites\/2\/2025\/06\/tech-ai-featured-img.jpg","width":1000,"height":563},{"@type":"WebSite","@id":"https:\/\/ibkrcampus.com\/campus\/#website","url":"https:\/\/ibkrcampus.com\/campus\/","name":"IBKR Campus US","description":"Financial Education from Interactive Brokers","publisher":{"@id":"https:\/\/ibkrcampus.com\/campus\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/ibkrcampus.com\/campus\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/ibkrcampus.com\/campus\/#organization","name":"Interactive Brokers","alternateName":"IBKR","url":"https:\/\/ibkrcampus.com\/campus\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/ibkrcampus.com\/campus\/#\/schema\/logo\/image\/","url":"https:\/\/www.interactivebrokers.com\/campus\/wp-content\/uploads\/sites\/2\/2024\/05\/ibkr-campus-logo.jpg","contentUrl":"https:\/\/www.interactivebrokers.com\/campus\/wp-content\/uploads\/sites\/2\/2024\/05\/ibkr-campus-logo.jpg","width":669,"height":669,"caption":"Interactive Brokers"},"image":{"@id":"https:\/\/ibkrcampus.com\/campus\/#\/schema\/logo\/image\/"},"publishingPrinciples":"https:\/\/www.interactivebrokers.com\/campus\/about-ibkr-campus\/","ethicsPolicy":"https:\/\/www.interactivebrokers.com\/campus\/cyber-security-notice\/"},{"@type":"Person","@id":"https:\/\/ibkrcampus.com\/campus\/#\/schema\/person\/be0fc850f28388c089a16534ce09be74","name":"Elisabetta Basilico, Ph.D., CFA","url":"https:\/\/www.interactivebrokers.com\/campus\/author\/elisabettabasilico\/"}]}},"jetpack_featured_media_url":"https:\/\/www.interactivebrokers.com\/campus\/wp-content\/uploads\/sites\/2\/2025\/06\/tech-ai-featured-img.jpg","_links":{"self":[{"href":"https:\/\/ibkrcampus.com\/campus\/wp-json\/wp\/v2\/posts\/231190","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ibkrcampus.com\/campus\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ibkrcampus.com\/campus\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ibkrcampus.com\/campus\/wp-json\/wp\/v2\/users\/152"}],"replies":[{"embeddable":true,"href":"https:\/\/ibkrcampus.com\/campus\/wp-json\/wp\/v2\/comments?post=231190"}],"version-history":[{"count":0,"href":"https:\/\/ibkrcampus.com\/campus\/wp-json\/wp\/v2\/posts\/231190\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/ibkrcampus.com\/campus\/wp-json\/wp\/v2\/media\/225517"}],"wp:attachment":[{"href":"https:\/\/ibkrcampus.com\/campus\/wp-json\/wp\/v2\/media?parent=231190"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ibkrcampus.com\/campus\/wp-json\/wp\/v2\/categories?post=231190"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ibkrcampus.com\/campus\/wp-json\/wp\/v2\/tags?post=231190"},{"taxonomy":"contributors-categories","embeddable":true,"href":"https:\/\/ibkrcampus.com\/campus\/wp-json\/wp\/v2\/contributors-categories?post=231190"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}