Demographic synthetic survey panels are often validated by matching aggregate answers to published surveys. We test what that certificate establishes across six multiselect batteries from four survey organisations in three countries. The headline analysis is restricted to three instruments whose synthetic cohort and hu...
Large language models (LLMs) are increasingly used for automated data visualization, yet existing approaches often frame visualization generation as a single-step mapping from user query to figure or code, overlooking the iterative analytical reasoning process of expert analysts. We present InsightChain, a four-stage v...
Han-Ya Sun, Chen Zhang, Sheng Liang et al.· 0 citations
A counterfactual condition (MIX) is test with a counterfactual condition (MIX) in which each document combines segments drawn from different systems, preserving document-level presentation while breaking cross-segment consistency.
Ahrii Kim, Vilém Zouhar, Chanjun Park et al.· 0 citations
This work conducts a controlled human study of six reasoning formats across tasks of varying complexity, supported by a web-based framework that randomizes task domains, problem instances, and representation order.
Jaewoo Lim, Sungbok Shin, San Hong· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This paper examines Turing's 1948 report, "Intelligent Machinery", as an important conceptual source for the later imitation games. Its first contribution is to identify and integrate the design concepts underlying the 1948 chess-based imitation game: the possibility that intelligent machines may make mistakes, the exc...
The findings suggest that open-source models, when trained with community-derived preference signals, can support high-quality mental health support assistance while offering a more privacy-preserving alternative for sensitive support contexts.
J. Kim, Maya Ajit, S. Gong et al.· arXiv.org· 4 citations
Recent developments in AI safety research have called for red-teaming methods that effectively surface potential risks posed by generative AI models, with growing emphasis on how red-teamers' backgrounds and perspectives shape their strategies and the risks they uncover. While automated red-teaming approaches promise t...
Wesley Hanwen Deng, Mingxi Yan, Sunnie S. Y. Kim et al.· 0 citations
Mobile GUI agents can automate smartphone tasks by interacting directly with app interfaces, but how they should communicate with users during execution remains underexplored. Existing systems rely on two extremes: foreground execution, which maximizes transparency but prevents multitasking, and background execution, w...
Jeonghyeon Kim, Byeongjun Joung, Junwon Lee et al.· 0 citations
A unified framework for evaluating LLM uncertainty based on Hill numbers, a family of diversity measures, is introduced, which provides a common and intuitive scale for interpreting variation in LLM outputs while accommodating different notions of semantic similarity and different sensitivities to output distributions.
Is an LLM telling you different facts than it's telling me? This paper introduces ConsistencyAI, an independent benchmark for measuring the factual consistency of large language models (LLMs) for different personas. ConsistencyAI tests whether, when users of different demographics ask identical questions, the model res...
Peter Banyas, Shristi Sharma, Alistair Simmons et al.· 0 citations
A human's moral decision depends heavily on the context. Yet research on LLM morality has largely studied fixed scenarios. We address this gap by introducing Contextual MoralChoice, a dataset of moral dilemmas with systematic contextual variations known from moral psychology to shift human judgment: consequentialist, e...
As AI writing tools become widespread, we need to understand how both humans and machines evaluate literary style, a domain where objective standards are elusive and judgments are inherently subjective. We conducted controlled experiments using Raymond Queneau's Exercises in Style (1947) to measure attribution bias acr...
Students in MIT’s Concourse program delve deeply into the human condition, debate challenging questions, and learn to develop judgment about issues that can’t be quantified.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduSep 30, 2026
Able to defeat top-ranked human players and more efficient than other models, the new system could help decision-makers in military maneuvers or business negotiations.
Computer scientist, entrepreneur, and philanthropist will collaborate with the MIT Schwarzman College of Computing to advance AI and scientific discovery.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
