Category
9,261 papers
Large language models can convincingly adopt personas, recall past dialogues, and weave rich autobiographies. Yet this conversational eloquence conceals a fundamental attribution problem: looking the part does not mean having lived the life. Two individuals can share identical public profiles--the same age, hometown, o...
A two-stage audit of demographic leakage in German-language LLM-generated resumes demonstrates that apparently neutral resume generation can still preserve highly predictive demographic signals, raising concerns about anonymization-based fairness interventions in multilingual AI hiring pipelines.
SCoR advances research-direction forecasting from predicting which concepts will co-occur to anticipating whether and how evidence-backed scientific relations will emerge, and introduces HiSCoR, a task-adapted model family that models relation emergence as a temporally evolving, hierarchically constrained process.
This framework introduces a Joint-Factor Embedding Retrieval module to locate similar recipes with specified sodium content for addressing the lack of contextual references, and designs a structured 4-hop Chain-of-Thought inference module to refine the vague estimation from language models through a multi-step sodium e...
Reach audiences
Advertise in front of researchers, engineers, and readers.
MedNotes is a multi-agent synthetic data generation pipeline that converts longitudinal structured EHR into source-grounded clinical note representations under explicit quality control and improves downstream CPT prediction and paragraph-level section prediction when combined with limited real data.
FedRepRAG is proposed, a decentralized RAG framework that keeps raw documents at their owning clients and exchanges only compact latent representations during cross-client retrieval, and provides an effective and efficient framework for federated RAG without transferring raw retrieved content.
Medical large language models are commonly trained on mixtures of didactic data (e.g., textbooks) and clinical data (e.g., patient records), yet how these data types differentially shape model capabilities remains unclear. We address this issue with token-matched experiments that vary the didactic-to-clinical ratio and...
Comparing supervised fine tuning and Group Relative Policy Optimization against an untrained baseline on a four tier Constraint Awareness Benchmark shows the reward based signal is the more destructive of the two: a reward that penalizes banned ingredient tokens regardless of framing learns a context independent suppre...
A projection-based evaluator for tabular--text synthetic data and results support explicit cross-modal evaluation with permutation baselines and coverage reporting support cross-modal evaluation with permutation baselines and coverage reporting.
MMSAFE is proposed, a multi-layer framework for multilingual safety-degrading data identification that captures both shared and language-specific safety signals and reduces the average harmful-response ratio compared with random filtering and achieves stronger average performance than the strongest single-layer baselin...
The use of composition operators are introduced, which generalize the Koopman operator and can map between distinct spaces, motivating the perspective that LLM transformations are rectangular infinite-dimensional operators.
It is found that the hallucination signal survives code-mixing well: transfer AUROC ranges from 0.88 to 0.99, with gaps of mostly under 0.05 AUROC relative to in-distribution performance, and that Hindi-trained probes transfer to Hinglish more reliably than English-trained probes.
A Blog post by Ai2 on Hugging Face
A Blog post by IBM Research on Hugging Face
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.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
