Knowledge graph-to-text (KG-to-text) generation verbalizes a set of knowledge graph triples into fluent natural language. While fine-tuned encoder-decoder models have long been the standard approach, recent LLMs are becoming increasingly competitive. We benchmark recent LLMs against fine-tuned encoder-decoder models, u...
Priyanka, Renaud Delbru, Souhail Bakkali et al.· 0 citations
Metaphor is a crucial aspect of human cognition. As such, we would like to understand how it is represented in large language models (LLMs) and how it might be controlled. We use mechanistic interpretability techniques to identify causal subspaces in a range of LLMs covering different architectures and sizes. We show t...
Users increasingly rely on AI systems for extended, multi-turn tasks, yet evidence indicates that LLM-based system performance degrades over prolonged interaction. To evaluate and improve AI assistants in such settings, we need user simulators that faithfully follow complex user intents while exhibiting realistic conve...
Mustafa Omer Gul, Philippe Laban, Tanya Goyal et al.· 0 citations
This work investigates evidence-grounded health summarization for menstrual health monitoring using a constrained generation framework that combines structured evidence conditioning with Retrieval-Augmented Generation (RAG) using a prompt-based constrained generation framework and evaluates semantic alignment using Nat...
Bayram Ayadi, Florian Geissler, Johanna Schmidhuber· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Recent advances in specialized decision models have expanded the possibilities for zero-shot classification, yet their effectiveness on Vietnamese remains underexplored. This study evaluates four specialized decision models across 13 classification settings spanning six task groups, examining zero-shot performance, sen...
Phat Huu Ha, Nguyen Xuan Phuc, Nong Nhut Quy et al.· 0 citations
Code-switched (CS) automatic speech recognition (ASR) remains difficult because real CS speech is scarce and synthetic speech does not fully match it. We investigate whether synthetic CS speech is more useful for learning an adaptation-friendly initialization than for ordinary continual fine-tuning. We propose SyRA-CS,...
Fadel Thior, Ahmer Tabassum, Haania Siddiqui et al.· 0 citations
Multilingual language models can give different identity judgments when the same people's names are written in different scripts. We study this effect using 601 audited identity pairs with attested Devanagari and Latin forms, holding the question and relation fixed. Qwen2.5-7B's same-person accuracy falls from 35.1% in...
Bashkir is a low-resource agglutinative language written in Cyrillic and remains poorly represented in modern LLMs. We present an open resource suite and a systematic benchmark of adaptation methods: the Bashkir Web Corpus (71,567 documents, 46.9M tokens, 16 sources) and three labelled datasets for binary, multiclass a...
CrisiLangs, a multilingual extension of CrisiText, is presented, a multilingual extension of CrisiText, to Italian, Bulgarian, German, and Greek, where low decoding temperatures receive the most preferences in all five languages and in both configurations, while the effect of the guidelines varies by language.
Giacomo Gonella, S. Menini, Marco Guerini· 0 citations
Most automated survey generation systems retrieve papers as flat documents, limiting their ability to capture research structure. We present SurveyGraph, a framework built around a Methods-Entity Knowledge Graph (MEKG) encoding method-level follow-on, competition, and shared-resource relations. The graph supports core-...
Yi-Fan Yuan, Yan-Cheng Zhu, Zuo-Yu Zhang et al.· Conference on Empirical Meth...· 0 citations
Large language models can repeat an instruction while failing to keep obeying it. We study this recall-compliance dissociation in long-horizon dialogue and define State Integrity Collapse: a model preserves a stated constraint in memory but stops applying it to later turns. We introduce StateTrack-Bench, a controlled s...
Yan-Cheng Zhu, Yi-Fan Yuan· Proceedings of the 2026 Conf...· 0 citations
Hierarchical language generation separates continuous semantic modeling from discrete text realization, but its effectiveness depends on what the latent space compresses and how the discrete generator uses it. We propose Cola2, a framework that jointly studies continuous semantic compression, the balance between recons...
Hongcan Guo, Yian Zhao, Feng Wang 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.
