In statutory question answering, every claim must be traceable to evidence, not merely relevant, since unverifiable labour-rights answers carry serious legal consequences. Current systems fall short: single-pass RAG cannot detect insufficient evidence, while multi-agent legal-debate systems treat grounding as a prompti...
Fatema Tuj Johora Faria, Mukaffi Bin Moin, Jubayer Al Mahmud et al.· 0 citations
A lightweight hierarchical attribution model is trained that predicts safety violations and attributes them to contributing user turns and token spans and preserves low false positive rates on benign conversations with high-risk vocabulary.
Srinivasan Subramanian, Kazi Aminul Islam, Md Abdullah Al Hafiz Khan· 0 citations
DeBERTa-based and T5-based models that rank HTML elements by their relevance to the task and a zero-shot ColBERT-based retriever that is able to retrieve the ground-truth element with a recall of 0.52 on Mind2Web and 0.47 on WebArena are developed.
Safety alignment in large language models is trained primarily in English, and recent work reports that the underlying harmfulness representation survives translation: English-trained probes separate harmful from harmless prompts almost as well in low-resource languages as in English. This has been taken as evidence th...
Paras Balani, Subhrakanta Panda· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Researchers in industry and academia use synthetic survey respondents powered by large language models as substitutes for human samples. These synthetic populations require validation against real-world data, so researchers often address them using ad hoc comparisons with human surveys. Inspired by the intention-behavi...
F. Kutzner, C. Kacperski, Laura de Molière et al.· 1 citation
Jev has the lowest cost and median response time among the evaluated configurations, while hosted language models achieve higher baseline accuracy and Rankings by baseline accuracy differ from rankings by correctness across every condition and repeat, although small differences in the latter do not establish a general...
Fan Zhang, Yan-Kai Chen, Zhuo-Han Xie et al.· 13 citations· ⚡1
This work isolates SLM graph reasoning from navigation and traceability capability by employing the THESEUS navigation and traceability framework and using frozen, off-the-shelf SLMs as local action policies, and results motivate evaluating SLM graph reasoning beyond endpoint accuracy alone.
Eduin E. Hernandez, Sergio A. Diaz, Luis F. Garcia et al.· 0 citations
This survey connects Articulated, Inner and Perceived tasks to the neural populations they engage, the representations available to decoders and the outputs those representations can support, and outlines a prospective five-level trajectory from commands and language to meaning, scenarios and bidirectional cognitive ex...
Yi-Qian Yang, Yi-Qun Duan, Chen-Yu Liu et al.· 1 citation
Findings and error-scope analyses show that benchmark agreement reflects report size and error definitions as well as medical error detection, and local RadMatch achieves stronger agreement on clinically significant errors in both expert datasets and on total errors in the shared RadEvalExpert subset.
Jia-Ju Huang, Hao Yang, Xin-Yu Ma et al.· 7 citations· ⚡1
J-ICL is proposed, a post-training framework that incorporates context validation into the training objective and improves ICLEval and reality accuracy by an average of 5.84 percentage points and reality accuracy by 9.20 points over the corresponding base models.
Pei-Lin Li, Qing-Le Liu, Jun-Yang Feng et al.· 0 citations
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.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
