This work proposes a two-stage framework to assess the severity of false claims during disasters, and investigates false claim severity assessment as a human-AI alignment problem, evaluating whether models can reproduce human judgments under a shared evaluation rubric rather than merely predicting severity labels.
Ruichen Yao, Tejna Dasari, G. Baispay et al.· Proceedings of the 2026 ACM...· 0 citations
The study reveals a gap between reviewers'intentions and actual reviewing behaviour, highlighting the need for software companies to revisit their AI policies to better support developers in reviewing LLM-generated code.
Ranim Khojah, F. D. de Oliveira, Mazen Mohamad et al.· arXiv.org· 0 citations
An observational study of 20,574 coding-agent sessions from 1,639 repositories across IDE and CLI workflows operationalizes misalignment as a breakdown made visible through developer pushback, and annotates each episode along four axes: form, cause, cost, and resolution.
This paper introduces a practical and unified approach to real-time adaptive experiments that can encompass these scenarios across textual, visual, and audio tasks and describes an adaptive treatment assignment strategy that identifies the optimal treatment up to three times as accurately as a fixed design.
Lucas Gautheron, Nori Jacoby, Peter M. C. Harrison· arXiv.org· 1 citation
Reach audiences
Advertise in front of researchers, engineers, and readers.
TailorCoPilot demonstrates a viable pathway to capture practice-based expertise, operationalizing it to support both generative AI advancements and human apprenticeship.
Yue Sun, Zhao-Hui Wang, Ruiyang Liu et al.· 0 citations
SemanticSlider3D is presented, a technique for continuous semantic attribute editing of 3D objects that requires no per-attribute training and supported decision-making in 3D prototyping and was perceived as a valuable addition to existing workflows.
Ru Wang, Rahul Jain, Koichiro Niinuma et al.· 0 citations
This work pauses a reflection-support agent when it would normally redirect the conversation, surface its observation, and asks users to interpret the pattern and decide how to proceed, and derives a taxonomy of nine interpretation categories and shows that similar reflective states can call for substantially different...
This work introduces RAGE-Vis, a Relation-Aware Generative Editing interface for natural language-based chart editing, and demonstrates the applicability of RAGE-Vis in complex editing tasks, including style adjustment, data extension, order rearrangement, legend layout, and color mapping.
Ziyao Kang, Yiping Sun, L. Tian et al.· 0 citations
The AI Companion Vulnerability-Response Taxonomy is introduced, a grounded, paired taxonomy of user vulnerability and chatbot response designed for analyzing extended companion chatbot interactions and reveals distinct response profiles of AI companions in conversations with vulnerable users.
A novel multimodal framework that integrates egocentric vision, pupillometry, eye-gaze tracking, posture detection, heart activity, and the inferencing capabilities of large language models (LLMs) to create a proactive and context-aware ecosystem that dynamically adapts to users' psychophysiological states while analyz...
A. Rao, Utkarsh Agarwal, Amol Harsh et al.· arXiv.org· 0 citations
LatentGandr is a visual analytics technique that facilitates latent space exploration by extracting locally linear dimensions from embeddings in high-dimensional latent spaces by analyzing the topology and local curvature of the embeddings, and automatically identifies local neighborhoods and computes their principal c...
Empirical evidence is provided for understanding the "double-edged sword" effect of LLM-NPCs on player experience, and the importance of scenario-sensitive and user-sensitive design in intelligent NPC systems is highlighted.
T. Hsu, Wen-Ran Chen, Jiang-Xu Lin et al.· arXiv.org· 4 citations
AI agents can generate code at a scale that’s hard for humans to review line-by-line. PDD Kit helps ensure the code is doing what the developer intended by creating formal specifications and testing against them. It converts developer intent into a Verus specification, proves AI-generated code meets it for every input, and uses tests where proofs aren't practical. Developers review intent, not every line. The post Formally verifying agent-written full-stack web apps with PDD Kit appeared first o…
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
MIT News · Artificial Intelligence· news.mit.eduOct 23, 2026
During the School of Humanities, Arts, and Social Sciences’ 75th Anniversary Symposium, President Sally Kornbluth said “MIT has never needed your particular insight and guidance more than we do now.”
MIT News · Artificial Intelligence· news.mit.eduOct 23, 2026
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
MIT News · Artificial Intelligence· news.mit.eduOct 22, 2026
“X-Hinges” helps design and 3D print items like lamps and gloves with an interactive twist: automatically embedded sensors that perceive and adaptively respond to human contact.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
