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
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
Results show that reliability cannot be inferred from single-turn instruction following alone; evaluation must track whether remembered constraints remain operational as dialogue state grows, and introduces StateTrack-Bench, a controlled suite of conversations covering numerical, format, role/persona, factual-memory, a...
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
CoWriter is introduced, a proactive agentic scheme that adapts expert human (co-)authoring methodologies from cognitive science to flexibly steer the entire writing workflow while actively encouraging the user to engage.
Shmuel Amar, Benjamin Lieber, Ori Shapira et al.· 0 citations
Memory enables language model assistants to maintain continuity across sessions and generate personalized responses, but knowing more about a user does not necessarily produce responses they prefer. Existing evaluations assess memory capabilities without directly establishing whether memory use benefits the user. To st...
Yijiang River Dong, Ze-Xue He, Cheng Yu et al.· 0 citations
Search is a central component of Automatic Speech Recognition (ASR) systems and has been deeply investigated for classical ASR modeling based on Hidden Markov Models (HMMs). However, in work on current sequence-to-sequence ASR architectures it is often simplified to a small fixed-size beam search without external Langu...
Simon Berger, Larissa Kleppel, Ralf Schl\"uter· 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.
