Patient simulators are gaining traction in mental health training by providing scalable exposure to complex and sensitive patient interactions. Simulating depressed patients is challenging, as safety constraints and high patient variability complicate simulations and underscore the need for simulators that capture dive...
We study a QA curation pipeline for improving long-context complex reasoning in large language models (LLMs). Our approach, $\pi^2$, constructs high-quality reasoning data through rigorous QA curation: 1) extracting and expanding tables from Wikipedia, 2) from the collected tables together with relevant metadata, gener...
Quyet V. Do, Thinh Pham, Nguyen Nguyen et al.· 0 citations
Markdown carries structure a parser reads for free: headers, section paths, and block boundaries. Many RAG pipelines also spend LLM calls per chunk on generated metadata. We ask what one LLM call per chunk buys over that free structure. MDKeyChunker splits Markdown into header-led chunks without splitting any block; ma...
We propose a fully automated AI system that produces short comedic videos similar to sketch shows such as Saturday Night Live. Starting from character references, the system employs a population of agents loosely modeled on roles in real production studios and structured to optimize the quality and diversity of ideas a...
Susung Hong, Brian Curless, Ira Kemelmacher-Shlizerman et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
A systematic evaluation of LLM susceptibility to persuasion under the SMCR communication framework highlights substantial model-dependent limits of current robustness interventions and offers guidance for developing more trustworthy LLMs.
Agentic task-oriented dialogue (TOD) requires systems to track concurrent goals, dependencies, and long-horizon state. We examine goal-lifecycle recovery from fixed dialogue trajectories. ATOD contains 1,000 synthetic dialogues annotated for six advanced-TOD properties, and ATOD-Eval defines metrics for dependency-sens...
Yifei Zhang, Hooshang Nayyeri, Rinat Khaziev et al.· 0 citations
Matching place names across writing systems is a persistent obstacle to integrating multilingual geographic sources, from modern gazetteers to medieval itineraries and colonial-era surveys. Existing approaches rely on language-specific phonetic algorithms or on romanisation that discards phonetic information, and none...
EulerESG combines (i) dual-channel retrieval and LLM-driven disclosure analysis over ESG reports, and (ii) an interactive dashboard and chatbot for exploration, benchmarking, and explanation.
Yi Ding, Xu-Shuo Tang, Zheng-Yi Yang et al.· arXiv.org· 5 citations· ⚡1
The data and evaluation harness for Oolong is released, a benchmark of long-context reasoning tasks that require analyzing individual chunks of text on an atomic level, and then aggregating these analyses to answer distributional questions.
Multimodal retrieval, which seeks to retrieve relevant content across modalities such as text or image, supports applications from AI search to contents production. Despite the success of separate-encoder approaches like CLIP aligning modality-specific embeddings with contrastive learning, recent multimodal large langu...
Qiyu Wu, Shuyang Cui, Satoshi Hayakawa et al.· 0 citations
Hybrid thinking enables LLMs to switch between reasoning and direct answering, offering a balance between efficiency and reasoning capability. Yet our experiments reveal that current hybrid thinking LLMs only achieve partial mode separation: reasoning behaviors often leak into the no-think mode. To understand and mitig...
Shouren Wang, Wang Yang, Xianxuan Long et al.· 0 citations
Autonomous agents executing human instructions must operate reliably even when instructions are incomplete. While recent approaches improve detection of missing information, detection alone is insufficient: agents often proceed to execution even after recognizing underspecification, leading to incorrect or unsafe actio...
Swarnadeep Bhar, Omar Naim, Eleni Metheniti 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.
