Structured extraction of evidence from clinical trial publications underpins systematic reviews and clinical guidelines, yet large language models are adopted for it only hesitantly: their outputs are difficult to verify, their use commonly requires transmitting documents to proprietary services, and they do not improv...
Naman Ahuja, Abhijit Chakraborty, Muhammad Ali Khan et al.· 0 citations
Findings indicate that stylistic and structural properties of text provide a robust basis for distinguishing AI-generated misinformation from human-written fake news.
Samuel Jaeger, Calvin Ibeneye, Aya Vera-Jimenez et al.· arXiv.org· 2 citations
Active learning (AL) is a training paradigm for selecting unlabeled samples for annotation to improve model performance on a test set, which is useful when only a limited number of samples can be annotated. These algorithms often work by optimizing for the informativeness and diversity of the training data to be annota...
Lorenzo Jaime Yu Flores, Cesare Spinoso di-Piano, Ori Ernst et al.· 0 citations
SQLStructEval is introduced, a framework that analyzes this behavior through canonical abstract syntax tree representations and adopts a pipeline that first generates structured intermediate representations and then deterministically compiles them into SQL, improving execution accuracy and structural agreement among co...
Yi-Xi Zhou, Fan Zhang, Zhiyu Guo et al.· arXiv.org· 1 citation
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work reframing proposal generation as a time-sliced scientific forecasting problem, given a research question and inspiring papers available before a cutoff time, and operationalizes this objective with the Future Alignment Score (FAS), computed via retrieval and LLM-based semantic scoring against a held-out futur...
Heng Wang, Pengcheng Jiang, Jiashuo Sun et al.· arXiv.org· 5 citations
This work introduces a multi-agent framework designed to perform problem evolution while validating the solvability and increased difficulty of the generated problems, and provides empirical evidence that code-driven agents can serve as a viable mechanism for synthesizing high-difficulty mathematical reasoning problems...
Dadi Guo, Yue-Jin Xie, Qing-Yu Liu et al.· 0 citations
Presenting task-relevant information clearly is associated with better immediate revision performance and is favorably evaluated across learner profiles, while descriptive differences in evaluation patterns are observed, particularly for informational novelty and affective framing.
Momoka Furuhashi, Kouta Nakayama, N. Kawai et al.· 1 citation
This work leverage Mixture of Factor Analyzers (MFA) as a scalable, unsupervised alternative that models the activation space as a collection of Gaussian regions with their local covariance structure, and positions local geometry, expressed through subspaces, as a promising unit of analysis for scalable concept discove...
Or Shafran, S. Ronen, Omri Fahn et al.· arXiv.org· 10 citations· ⚡2
On-policy Verbal Distillation is introduced, a framework that uses verbal scores from black-box teachers to rank student-generated sub-trajectories, retaining high-scoring ones and replacing low-scoring ones with teacher-generated continuations and suggests that retaining student-generated prefixes helps preserve explo...
Jing Xiong, Hui Shen, Shansan Gong et al.· arXiv.org· 8 citations
David-GRPO addresses the challenge of small language model agents under the budget constraint of commodity GPUs by placing a handful of off-policy expert trajectories into the GRPO groups of the early updates, and rewarding evidence coverage and resumes the most promising partial trajectory.
Hojae Han, Hee-Yeon Jung, Jongyoon Kim et al.· arXiv.org· 1 citation
Hallucination in large language models (LLMs) remains an acute concern, contributing to the spread of misinformation and diminished public trust, particularly in high-risk domains. Among hallucination types, factuality is crucial, as it concerns a model's alignment with established world knowledge. Adversarial factuali...
Adam Szelestey, Sofie van Engelen, Tianhao Huang et al.· 0 citations
Noise-Aware Verbal Confidence CAlibration Rules are proposed to provide a principled foundation for resolving overconfidence under noise and NOVA, a noise-aware calibration framework that synthesizes supervision from ~2K HotpotQA examples guided by these rules.
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Microsoft Research Blog· microsoft.comOct 15, 2026
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduSep 24, 2026
