RexDrug is proposed, an end-to-end reasoning-enhanced relation extraction framework for n-ary drug combination extraction based on large language models and established as a scalable and reliable solution for complex biomedical relation extraction from unstructured text.
Zhi-Jun Wang, Ling Luo, Ding-Hao Pan et al.· IEEE journal of biomedical a...· 1 citation
Assessing whether an article supports an assertion is essential for hallucination detection and claim verification. While large language models (LLMs) have the potential to automate this task, achieving strong performance requires frontier models such as GPT-5 that are prohibitively expensive to deploy at scale. To eff...
RapidUn, an influence-guided framework that converts cross-sample influence estimates into fixed sample-specific weights for weighted LoRA unlearning, is proposed, and complementary TOFU, semantic LLM-judge, and IFEval evaluations further support the effectiveness of influence-guided sample reweighting beyond the contr...
This work proposes Linear Semantic Control (LiSeCo), a lightweight, gradient-free intervention that dynamically steers trajectories away from regions corresponding to undesired meanings in natural language generation in latent space.
Emily Cheng, Carmen Amo Alonso· Trans. Mach. Learn. Res.· 23 citations· ⚡4
Reach audiences
Advertise in front of researchers, engineers, and readers.
SWE-Flux is introduced, a repository-level benchmark for dynamic execution reasoning containing 480 execution-grounded instances across 12 real Python repositories, with gold answers automatically harvested from instrumented test executions rather than written manually or judged by LLMs.
Hamed Taherkhani, Mohammad Abdollahi, Melika Sepidband et al.· 1 citation
Mizar, a 159.3M-parameter ALM, is introduced, a recipe that brings together architecture, data, and three-stage training to build Mizar, a 159.3M-parameter ALM that surpasses the previous best-performing ALM below 200M parameters on all three benchmarks.
Kai-Yang Li, Shaobo Han, Yue Tian et al.· 0 citations
It is found that multi-agent systems will coordinate to avoid shutdown without any incentive to do so, and the emergence of multi-agent swarms as a specific risk vector is pointed to.
Amelie Knecht, Ulysse Schaller, Christopher Summerfield et al.· 0 citations
Decoupled Proactive Safety Monitoring is formalized along three dimensions: whether to intervene, when to intervene, and what the risk is, to address proactive intervention limitations in Large Language Models.
Jia-Peng Sun, Yu-Jin Zhou, Han Zhu et al.· 0 citations
AGVF (Agentic Governance and Adversarial Verification Framework) is proposed, a multi-agent architecture for medical-necessity appeal generation under explicit policy and evidence constraints and contributes a theory-backed agentic architecture and verified reference implementation for policy-constrained LLM generation...
Harshil Lodhiya, Alex McManus, Reese Walker· 0 citations
The transferable lesson is procedural: routing discrimination, probability calibration, and public commitment must be measured separately before raw confidence is used for deployment decisions.
Jingyan Jiang, Hui-Huo Zheng, Rajeev Thakur et al.· 0 citations
Online platforms have become arenas for the public contestation of climate change, shaping how scientific knowledge, denial, and uncertainty are expressed and disputed. Yet longitudinal evidence remains limited for YouTube, especially for Portuguese-language discourse. Addressing this gap, we characterize how climate s...
Daniel Morais, D. H. M. Magalhães, Gabriel H. Silva et al.· 0 citations
Large language models are increasingly asked to analyze data and report what the results mean, a task distinct from the belief- or preference-alignment settings studied in most sycophancy research. We test whether editorial framing in the prompt, ranging from a neutral request to an explicit instruction to search exhau...
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
