Paper: <a href=\"https://arxiv.org/abs/2606.11482\" rel=\"nofollow\">https://arxiv.org/abs/2606.11482</a><br>Code: <a href=\"https://github.com/ulab-uiuc/social-world-model\" rel=\"nofollow\">https://github.com/ulab-uiuc/social-world-model</a><br>Data: <a href=\"https://huggingface.co/datasets/ulab-ai/swm-bench\">https://huggingface.co/datasets/ulab-ai/swm-bench</a></p>\n","updatedAt":"2026-06-11T20:56:21.015Z","author":{"_id":"636453547cf2c0b4f0a3ee1e","avatarUrl":"/avatars/a453340b44d08eec2281ecbe5e993707.svg","fullname":"Haofei Yu","name":"lwaekfjlk","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":2,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6782823801040649},"editors":["lwaekfjlk"],"editorAvatarUrls":["/avatars/a453340b44d08eec2281ecbe5e993707.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.11482","authors":[{"_id":"6a2b204b4957fcdd3aac0526","name":"Haofei Yu","hidden":false},{"_id":"6a2b204b4957fcdd3aac0527","name":"Yining Zhao","hidden":false},{"_id":"6a2b204b4957fcdd3aac0528","name":"Guanyu Lin","hidden":false},{"_id":"6a2b204b4957fcdd3aac0529","name":"Jiaxuan You","hidden":false}],"publishedAt":"2026-06-09T22:15:51.000Z","submittedOnDailyAt":"2026-06-11T00:00:00.000Z","title":"Building Social World Models with Large Language Models","submittedOnDailyBy":{"_id":"636453547cf2c0b4f0a3ee1e","avatarUrl":"/avatars/a453340b44d08eec2281ecbe5e993707.svg","isPro":false,"fullname":"Haofei Yu","user":"lwaekfjlk","type":"user","name":"lwaekfjlk"},"summary":"Understanding and predicting how social beliefs evolve in response to events -- from policy changes to scientific breakthroughs -- remains a fundamental challenge in social science. Given LLMs' commonsense knowledge and social intelligence, we ask: Can LLMs model the dynamics of social beliefs following social events? In this work, we introduce the concept of the Social World Model (SWM), a general framework designed to capture how social beliefs evolve in response to major events. SWM learns state-transition functions for social beliefs by mining temporal patterns in social data and optimizing the evidence lower bound, without the need for explicit human annotations linking events to belief shifts, or for expensive census data. To evaluate SWM, we introduce a benchmark, SWM-bench, derived from real-world prediction markets, specifically Kalshi and Polymarket. SWM-bench includes over 12k data points for social belief prediction tasks spanning diverse domains such as politics, finance, and cryptocurrency. Our experimental results show that SWM significantly outperforms time-series foundation models, achieving state-of-the-art results on Kalshi data and demonstrating competitive performance on Polymarket data, while offering interpretable insights into the underlying mechanisms of social belief dynamics.","upvotes":1,"discussionId":"6a2b204b4957fcdd3aac052a","githubRepo":"https://github.com/ulab-uiuc/social-world-model","githubRepoAddedBy":"user","ai_summary":"Social World Model framework captures evolution of social beliefs in response to events through temporal pattern mining and evidence lower bound optimization without explicit human annotations.","ai_keywords":["Social World Model","state-transition functions","temporal patterns","evidence lower bound","prediction markets","Kalshi","Polymarket","social belief dynamics"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","githubStars":10,"organization":{"_id":"65448bef5b5d9185ba3202b9","name":"UIUC-CS","fullname":"University of Illinois at Urbana-Champaign","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/65448b21fcb96b8b48733729/ycqcXFayMTTD_KpE37067.jpeg"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"636453547cf2c0b4f0a3ee1e","avatarUrl":"/avatars/a453340b44d08eec2281ecbe5e993707.svg","isPro":false,"fullname":"Haofei Yu","user":"lwaekfjlk","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"65448bef5b5d9185ba3202b9","name":"UIUC-CS","fullname":"University of Illinois at Urbana-Champaign","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/65448b21fcb96b8b48733729/ycqcXFayMTTD_KpE37067.jpeg"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.11482.md"}">
Building Social World Models with Large Language Models
Abstract
Social World Model framework captures evolution of social beliefs in response to events through temporal pattern mining and evidence lower bound optimization without explicit human annotations.
Understanding and predicting how social beliefs evolve in response to events -- from policy changes to scientific breakthroughs -- remains a fundamental challenge in social science. Given LLMs' commonsense knowledge and social intelligence, we ask: Can LLMs model the dynamics of social beliefs following social events? In this work, we introduce the concept of the Social World Model (SWM), a general framework designed to capture how social beliefs evolve in response to major events. SWM learns state-transition functions for social beliefs by mining temporal patterns in social data and optimizing the evidence lower bound, without the need for explicit human annotations linking events to belief shifts, or for expensive census data. To evaluate SWM, we introduce a benchmark, SWM-bench, derived from real-world prediction markets, specifically Kalshi and Polymarket. SWM-bench includes over 12k data points for social belief prediction tasks spanning diverse domains such as politics, finance, and cryptocurrency. Our experimental results show that SWM significantly outperforms time-series foundation models, achieving state-of-the-art results on Kalshi data and demonstrating competitive performance on Polymarket data, while offering interpretable insights into the underlying mechanisms of social belief dynamics.
Community
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2606.11482 in a model README.md to link it from this page.
Cite arxiv.org/abs/2606.11482 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2606.11482 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.