AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Category
8,786 papers
We present Muslim, a production Arabic voice AI platform serving grounded, sourced Islamic knowledge to real users. Beyond a real-time voice pipeline (NeMo Arabic ASR, an OpenAI-compatible LLM endpoint, self-hosted TTS) and a deterministic multi-source retrieval layer routed across six Model Context Protocol servers, w...
A temporal alignment failure, stale-document poisoning, is identified, in which outdated evidence makes a model wrong despite answering correctly without retrieval, and the same internal components also support broader comparison tasks, suggesting that temporal applicability can recruit a general reasoning mechanism us...
It is shown that accounts are able to classify as ’scientists’ and ’non-scientists’ on two different datasets, reaching an F1-Macro score of up to 0.87 using Random Forests with linguistic features and up to 0.89 using a DeBERTa model in an ensemble setup.
PIA, a personal intelligence agent deployed alongside a consumer health agent, is presented, a personal intelligence agent deployed alongside a consumer health agent that receives the agent's natural-language requests, decides for itself whether and how to write or read, and turns conversations into typed clinical reco...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Individuals turn to large language models (LLMs) for guidance across a wide range of economic tasks, from comparing loan options and planning savings to deciding what raise to ask for or how much to charge for their services. LLMs are known to reproduce social biases, and biased economic guidance may influence what use...
Black-box model identification works by scoring a model's response to natural-language prompts. One line of work feeds models a degenerate input -- their own token, repeated -- to find a failure mode rather than an identity. We take that input and ask where the model goes when it does not. For each token t, read argmax...
We empirically investigate Question Under Discussion based modelling in naturalistic dialogue by studying whether the salience of generated potential questions predicts their subsequent resolution. Building on Wu et al. (2024), we construct a dataset of 7,124 questions automatically generated from utterances and preced...
Patient-facing AI assistants promise valuable support to patients, but incoming queries can pose medical risks. To create guardrails, we work with oncologists to define three ordinal risk axes: Medical Urgency, Psychological Urgency, and Topic Sensitivity. We propose Clinical Guardrail Probes (CG-Probes) to measure the...
This work evaluates two mid-size LLMs on 23 richly annotated, expert-labeled episodes across prompting conditions that vary definitional scaffolding, reasoning mode, and turn structure, finding no single configuration performs best across all sensemaking dimensions.
Open rerankers trained for general web retrieval transfer imperfectly to e-commerce, where ranking decisions depend not only on topical relevance but also on user preferences, product constraints, and comparative product fit. These preference signals are difficult to supervise at scale: real search traffic provides aut...
This analysis covers 364,941 responses from three frontier Chinese-based LLMs to 12,165 factual questions derived from real-world Chinese search queries, and evaluates the models with and without reasoning across baseline, belief-conditioned, and anti-sycophancy prompting, tracing matched shifts among correct, incorrec...
Tha, a Khmer text normalization and inverse text normalization toolkit built from weighted finite-state transducers, is presented, a Khmer text normalization and inverse text normalization toolkit built from weighted finite-state transducers.
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.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
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.
A new language-processing tool could help identify the highest-risk individuals from natural language, enabling swifter interventions.
A Blog post by Liquid AI on Hugging Face
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
