[
  {
    "key": "dellacqua2023",
    "title": "Navigating the Jagged Technological Frontier: Field Experimental Evidence of the Effects of Artificial Intelligence on Knowledge Worker Productivity and Quality",
    "authors": "Fabrizio Dell'Acqua, Edward McFowland III, Ethan Mollick, et al.",
    "year": 2026,
    "venue": "Organization Science (2026); first released as HBS Working Paper 24-013 (2023)",
    "evidence_type": "field experiment",
    "llm_tested": true,
    "url": "https://doi.org/10.1287/orsc.2025.21838",
    "doi": "10.1287/orsc.2025.21838",
    "arxiv": "2025.21838",
    "access": "full text (Organization Science, CC BY, via hbs.edu)",
    "cited_in": [
      "who-benefits",
      "make-users-think"
    ]
  },
  {
    "key": "feng2024cocoa",
    "title": "Cocoa: Co-Planning and Co-Execution with AI Agents",
    "authors": "K. J. Kevin Feng, Kevin Pu, Matt Latzke, et al.",
    "year": 2026,
    "venue": "CHI 2026 (arXiv:2412.10999v4)",
    "evidence_type": "system evaluation",
    "llm_tested": true,
    "url": "https://doi.org/10.1145/3772318.3791673",
    "doi": "10.1145/3772318.3791673",
    "arxiv": "2318.37916",
    "access": "full text (arXiv 2412.10999v4, CC BY)",
    "cited_in": [
      "agent-handoff"
    ]
  },
  {
    "key": "lee2025",
    "title": "The Impact of Generative AI on Critical Thinking: Self-Reported Reductions in Cognitive Effort and Confidence Effects From a Survey of Knowledge Workers",
    "authors": "Hao-Ping (Hank) Lee, Advait Sarkar, Lev Tankelevitch, et al.",
    "year": 2025,
    "venue": "CHI 2025",
    "evidence_type": "survey",
    "llm_tested": true,
    "url": "https://doi.org/10.1145/3706598.3713778",
    "doi": "10.1145/3706598.3713778",
    "arxiv": "6598.37137",
    "access": "full text (Microsoft Research PDF, CC BY)",
    "cited_in": [
      "deskilling"
    ]
  },
  {
    "key": "magentic2025",
    "title": "Magentic-UI: Towards Human-in-the-loop Agentic Systems",
    "authors": "Hussein Mozannar, Gagan Bansal, Cheng Tan, Adam Fourney, et al.",
    "year": 2025,
    "venue": "arXiv:2507.22358 (Microsoft Research, 2025)",
    "evidence_type": "system evaluation",
    "llm_tested": true,
    "url": "https://arxiv.org/abs/2507.22358",
    "arxiv": "2507.22358",
    "access": "full text (arXiv 2507.22358v1)",
    "cited_in": [
      "ask-before-acting",
      "agent-handoff"
    ]
  },
  {
    "key": "si2024",
    "title": "Large Language Models Help Humans Verify Truthfulness—Except When They Are Convincingly Wrong",
    "authors": "Chenglei Si, Navita Goyal, Sherry Tongshuang Wu, et al.",
    "year": 2024,
    "venue": "arXiv:2310.12558v2 (Apr 2024)",
    "evidence_type": "experiment",
    "llm_tested": true,
    "url": "https://arxiv.org/abs/2310.12558",
    "arxiv": "2310.12558",
    "access": "full text (arXiv 2310.12558v2)",
    "cited_in": [
      "llm-explanations",
      "chat-vs-search"
    ]
  },
  {
    "key": "brynjolfsson2023",
    "title": "Generative AI at Work",
    "authors": "Erik Brynjolfsson, Danielle Li, Lindsey Raymond",
    "year": 2024,
    "venue": "arXiv:2304.11771v2 (revised Nov 2024)",
    "evidence_type": "field study",
    "llm_tested": true,
    "url": "https://arxiv.org/abs/2304.11771v2",
    "arxiv": "2304.11771",
    "access": "",
    "cited_in": [
      "who-benefits"
    ]
  },
  {
    "key": "vasconcelos2023gen",
    "title": "Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions",
    "authors": "Helena Vasconcelos, Gagan Bansal, Adam Fourney, Q. Vera Liao, Jennifer Wortman Vaughan",
    "year": 2024,
    "venue": "ACM TOCHI (preprint, arXiv:2302.07248v3, Nov 2024)",
    "evidence_type": "experiment",
    "llm_tested": true,
    "url": "https://doi.org/10.1145/3702320",
    "doi": "10.1145/3702320",
    "arxiv": "2302.07248",
    "access": "full text (arXiv 2302.07248v3)",
    "cited_in": [
      "code-security",
      "highlight-uncertainty"
    ]
  },
  {
    "key": "mozannar2022",
    "title": "Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming",
    "authors": "Hussein Mozannar, Gagan Bansal, Adam Fourney, Eric Horvitz",
    "year": 2024,
    "venue": "arXiv:2210.14306v5 (revised Apr 2024)",
    "evidence_type": "observational study",
    "llm_tested": true,
    "url": "https://arxiv.org/abs/2210.14306v5",
    "arxiv": "2210.14306",
    "access": "",
    "cited_in": [
      "inline-suggestions"
    ]
  },
  {
    "key": "nahar2024",
    "title": "Fakes of Varying Shades: How Warning Affects Human Perception and Engagement Regarding LLM Hallucinations",
    "authors": "Mahjabin Nahar, Haeseung Seo, Eun-Ju Lee, et al.",
    "year": 2024,
    "venue": "COLM 2024",
    "evidence_type": "experiment",
    "llm_tested": true,
    "url": "https://arxiv.org/abs/2404.03745",
    "arxiv": "2404.03745",
    "access": "full text (arXiv 2404.03745)",
    "cited_in": [
      "hallucination-warnings"
    ]
  },
  {
    "key": "cohn2024",
    "title": "Believing Anthropomorphism: Examining the Role of Anthropomorphic Cues on Trust in Large Language Models",
    "authors": "Michelle Cohn, Mahima Pushkarna, Gbolahan O. Olanubi, et al.",
    "year": 2024,
    "venue": "CHI 2024 (author version, arXiv:2405.06079)",
    "evidence_type": "experiment",
    "llm_tested": true,
    "url": "https://arxiv.org/abs/2405.06079",
    "arxiv": "2405.06079",
    "access": "full text (arXiv 2405.06079v1)",
    "cited_in": [
      "anthropomorphism"
    ]
  },
  {
    "key": "altay2024",
    "title": "People are skeptical of headlines labeled as AI-generated, even if true or human-made, because they assume full AI automation",
    "authors": "Sacha Altay, Fabrizio Gilardi",
    "year": 2024,
    "venue": "PNAS Nexus 2024",
    "evidence_type": "experiment",
    "llm_tested": true,
    "url": "https://doi.org/10.1093/pnasnexus/pgae403",
    "doi": "10.1093/pnasnexus/pgae403",
    "access": "full text (Europe PMC, CC BY)",
    "cited_in": [
      "ai-labels"
    ]
  },
  {
    "key": "kim2024",
    "title": "“I'm Not Sure, But...”: Examining the Impact of Large Language Models' Uncertainty Expression on User Reliance and Trust",
    "authors": "Sunnie S. Y. Kim, Q. Vera Liao, Mihaela Vorvoreanu, Stephanie Ballard, Jennifer Wortman Vaughan",
    "year": 2024,
    "venue": "FAccT 2024",
    "evidence_type": "experiment",
    "llm_tested": true,
    "url": "https://arxiv.org/abs/2405.00623",
    "arxiv": "2405.00623",
    "access": "full text (arXiv 2405.00623v2)",
    "cited_in": [
      "show-confidence"
    ]
  },
  {
    "key": "padmakumar2024",
    "title": "Does Writing with Language Models Reduce Content Diversity?",
    "authors": "Vishakh Padmakumar, He He",
    "year": 2024,
    "venue": "ICLR 2024",
    "evidence_type": "experiment",
    "llm_tested": true,
    "url": "https://arxiv.org/abs/2309.05196",
    "arxiv": "2309.05196",
    "access": "full text (arXiv 2309.05196)",
    "cited_in": [
      "homogenization"
    ]
  },
  {
    "key": "zhang2024fair",
    "title": "“It's a Fair Game”, or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational Agents",
    "authors": "Zhiping Zhang, Michelle Jia, Hao-Ping (Hank) Lee, et al.",
    "year": 2024,
    "venue": "CHI 2024",
    "evidence_type": "qualitative study",
    "llm_tested": true,
    "url": "https://arxiv.org/abs/2309.11653",
    "arxiv": "2309.11653",
    "access": "full text (arXiv 2309.11653v2)",
    "cited_in": [
      "privacy-disclosure",
      "anthropomorphism"
    ]
  },
  {
    "key": "vasconcelos2023",
    "title": "Explanations Can Reduce Overreliance on AI Systems During Decision-Making",
    "authors": "Helena Vasconcelos, Matthew Jörke, Madeleine Grunde-McLaughlin, et al.",
    "year": 2023,
    "venue": "CSCW 2023 (arXiv 2022)",
    "evidence_type": "experiment",
    "llm_tested": false,
    "url": "https://arxiv.org/abs/2212.06823",
    "arxiv": "2212.06823",
    "access": "",
    "cited_in": [
      "explanations-trust"
    ]
  },
  {
    "key": "zamfirescu2023",
    "title": "Why Johnny Can't Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts",
    "authors": "J.D. Zamfirescu-Pereira, Richmond Y. Wong, Bjoern Hartmann, Qian Yang",
    "year": 2023,
    "venue": "CHI 2023",
    "evidence_type": "qualitative study",
    "llm_tested": true,
    "url": "https://doi.org/10.1145/3544548.3581388",
    "doi": "10.1145/3544548.3581388",
    "arxiv": "4548.35813",
    "access": "",
    "cited_in": [
      "blank-prompt"
    ]
  },
  {
    "key": "jakesch2023",
    "title": "Co-Writing with Opinionated Language Models Affects Users' Views",
    "authors": "Maurice Jakesch, Advait Bhat, Daniel Buschek, Lior Zalmanson, Mor Naaman",
    "year": 2023,
    "venue": "CHI 2023",
    "evidence_type": "experiment",
    "llm_tested": true,
    "url": "https://arxiv.org/abs/2302.00560",
    "arxiv": "2302.00560",
    "access": "",
    "cited_in": [
      "nudging-opinions",
      "homogenization"
    ]
  },
  {
    "key": "perry2023",
    "title": "Do Users Write More Insecure Code with AI Assistants?",
    "authors": "Neil Perry, Megha Srivastava, Deepak Kumar, Dan Boneh",
    "year": 2023,
    "venue": "CCS 2023",
    "evidence_type": "experiment",
    "llm_tested": true,
    "url": "https://doi.org/10.1145/3576915.3623157",
    "doi": "10.1145/3576915.3623157",
    "arxiv": "6915.36231",
    "access": "full text (arXiv 2211.03622v3)",
    "cited_in": [
      "deskilling",
      "code-security"
    ]
  },
  {
    "key": "liu2023",
    "title": "Evaluating Verifiability in Generative Search Engines",
    "authors": "Nelson F. Liu, Tianyi Zhang, Percy Liang",
    "year": 2023,
    "venue": "Findings of EMNLP 2023",
    "evidence_type": "audit",
    "llm_tested": true,
    "url": "https://arxiv.org/abs/2304.09848",
    "arxiv": "2304.09848",
    "access": "",
    "cited_in": [
      "citations"
    ]
  },
  {
    "key": "noy2023",
    "title": "Experimental evidence on the productivity effects of generative artificial intelligence",
    "authors": "Shakked Noy, Whitney Zhang",
    "year": 2023,
    "venue": "Science 381 (6654), 2023",
    "evidence_type": "experiment",
    "llm_tested": true,
    "url": "https://doi.org/10.1126/science.adh2586",
    "doi": "10.1126/science.adh2586",
    "access": "author manuscript of the Science paper (shakkednoy.com); abstract matches science.org",
    "cited_in": [
      "who-benefits"
    ]
  },
  {
    "key": "spatharioti2023",
    "title": "Comparing Traditional and LLM-based Search for Consumer Choice: A Randomized Experiment",
    "authors": "Sofia Eleni Spatharioti, David M. Rothschild, Daniel G. Goldstein, Jake M. Hofman",
    "year": 2023,
    "venue": "arXiv:2307.03744v2 (Nov 2023)",
    "evidence_type": "experiment",
    "llm_tested": true,
    "url": "https://arxiv.org/abs/2307.03744",
    "arxiv": "2307.03744",
    "access": "full text (arXiv 2307.03744v2)",
    "cited_in": [
      "hallucination-warnings",
      "chat-vs-search",
      "highlight-uncertainty"
    ]
  },
  {
    "key": "bansal2021",
    "title": "Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance",
    "authors": "Gagan Bansal, Tongshuang Wu, Joyce Zhou, et al.",
    "year": 2021,
    "venue": "CHI 2021 (arXiv 2020)",
    "evidence_type": "experiment",
    "llm_tested": false,
    "url": "https://arxiv.org/abs/2006.14779",
    "arxiv": "2006.14779",
    "access": "",
    "cited_in": [
      "llm-explanations",
      "explanations-trust"
    ]
  },
  {
    "key": "hohenstein2023",
    "title": "Artificial intelligence in communication impacts language and social relationships",
    "authors": "Jess Hohenstein, Dominic DiFranzo, Rene F. Kizilcec, et al.",
    "year": 2021,
    "venue": "arXiv:2102.05756v1 (2021); later in Scientific Reports",
    "evidence_type": "experiment",
    "llm_tested": false,
    "url": "https://arxiv.org/abs/2102.05756",
    "arxiv": "2102.05756",
    "access": "full text (arXiv 2102.05756v1)",
    "cited_in": [
      "ai-labels",
      "smart-replies"
    ]
  },
  {
    "key": "bucinca2021",
    "title": "To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making",
    "authors": "Zana Buçinca, Maja Barbara Malaya, Krzysztof Z. Gajos",
    "year": 2021,
    "venue": "CSCW 2021",
    "evidence_type": "experiment",
    "llm_tested": false,
    "url": "https://arxiv.org/abs/2102.09692",
    "arxiv": "2102.09692",
    "access": "",
    "cited_in": [
      "make-users-think"
    ]
  },
  {
    "key": "zhang2020",
    "title": "Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making",
    "authors": "Yunfeng Zhang, Q. Vera Liao, Rachel K. E. Bellamy",
    "year": 2020,
    "venue": "FAT* 2020",
    "evidence_type": "experiment",
    "llm_tested": false,
    "url": "https://arxiv.org/abs/2001.02114",
    "arxiv": "2001.02114",
    "access": "",
    "cited_in": [
      "show-confidence"
    ]
  },
  {
    "key": "cai2019",
    "title": "\"Hello AI\": Uncovering the Onboarding Needs of Medical Practitioners for Human-AI Collaborative Decision-Making",
    "authors": "Carrie J. Cai, Samantha Winter, David Steiner, Lauren Wilcox, Michael Terry",
    "year": 2019,
    "venue": "CSCW 2019",
    "evidence_type": "qualitative study",
    "llm_tested": false,
    "url": "https://doi.org/10.1145/3359206",
    "doi": "10.1145/3359206",
    "access": "abstract only",
    "cited_in": [
      "onboarding"
    ]
  },
  {
    "key": "kocielnik2019",
    "title": "Will You Accept an Imperfect AI? Exploring Designs for Adjusting End-user Expectations of AI Systems",
    "authors": "Rafal Kocielnik, Saleema Amershi, Paul N. Bennett",
    "year": 2019,
    "venue": "CHI 2019",
    "evidence_type": "experiment",
    "llm_tested": false,
    "url": "https://doi.org/10.1145/3290605.3300641",
    "doi": "10.1145/3290605.3300641",
    "arxiv": "0605.33006",
    "access": "full text (Microsoft Research PDF)",
    "cited_in": [
      "set-expectations"
    ]
  },
  {
    "key": "amershi2019",
    "title": "Guidelines for Human-AI Interaction",
    "authors": "Saleema Amershi, Dan Weld, Mihaela Vorvoreanu, et al.",
    "year": 2019,
    "venue": "CHI 2019",
    "evidence_type": "guidelines",
    "llm_tested": false,
    "url": "https://doi.org/10.1145/3290605.3300233",
    "doi": "10.1145/3290605.3300233",
    "arxiv": "0605.33002",
    "access": "",
    "cited_in": [
      "ask-before-acting",
      "set-expectations"
    ]
  },
  {
    "key": "ashktorab2019",
    "title": "Resilient Chatbots: Repair Strategy Preferences for Conversational Breakdowns",
    "authors": "Zahra Ashktorab, Mohit Jain, Q. Vera Liao, Justin D. Weisz",
    "year": 2019,
    "venue": "CHI 2019",
    "evidence_type": "experiment",
    "llm_tested": false,
    "url": "https://doi.org/10.1145/3290605.3300484",
    "doi": "10.1145/3290605.3300484",
    "arxiv": "0605.33004",
    "access": "full text (author PDF, qveraliao.com)",
    "cited_in": [
      "chatbot-repair"
    ]
  },
  {
    "key": "dietvorst2018",
    "title": "Overcoming Algorithm Aversion: People Will Use Imperfect Algorithms If They Can (Even Slightly) Modify Them",
    "authors": "Berkeley J. Dietvorst, Joseph P. Simmons, Cade Massey",
    "year": 2018,
    "venue": "Management Science",
    "evidence_type": "experiment",
    "llm_tested": false,
    "url": "https://doi.org/10.1287/mnsc.2016.2643",
    "doi": "10.1287/mnsc.2016.2643",
    "arxiv": "2016.2643",
    "access": "full text (Wharton faculty PDF)",
    "cited_in": [
      "let-users-edit"
    ]
  },
  {
    "key": "dietvorst2015",
    "title": "Algorithm aversion: People erroneously avoid algorithms after seeing them err",
    "authors": "Berkeley J. Dietvorst, Joseph P. Simmons, Cade Massey",
    "year": 2015,
    "venue": "Journal of Experimental Psychology: General",
    "evidence_type": "experiment",
    "llm_tested": false,
    "url": "https://doi.org/10.1037/xge0000033",
    "doi": "10.1037/xge0000033",
    "access": "",
    "cited_in": [
      "let-users-edit"
    ]
  },
  {
    "key": "lee2004",
    "title": "Trust in Automation: Designing for Appropriate Reliance",
    "authors": "John D. Lee, Katrina A. See",
    "year": 2004,
    "venue": "Human Factors",
    "evidence_type": "review",
    "llm_tested": false,
    "url": "https://doi.org/10.1518/hfes.46.1.50_30392",
    "doi": "10.1518/hfes.46.1.50_30392",
    "access": "abstract only",
    "cited_in": [
      "show-confidence"
    ]
  },
  {
    "key": "horvitz1999",
    "title": "Principles of mixed-initiative user interfaces",
    "authors": "Eric Horvitz",
    "year": 1999,
    "venue": "CHI 1999",
    "evidence_type": "principles",
    "llm_tested": false,
    "url": "https://doi.org/10.1145/302979.303030",
    "doi": "10.1145/302979.303030",
    "arxiv": "2979.30303",
    "access": "",
    "cited_in": [
      "ask-before-acting"
    ]
  }
]