Large Language Models (LLMs) achieve excellent performance in natural language reasoning tasks through pre-training on vast unstructured text, enabling them to understand the logic in natural language and generate logic-consistent responses. However, the representational differences between unstructured and structured...
Songze Li, Zhiqiang Liu, Zhaoyan Gong et al.· 0 citations
Large Language Models (LLMs) exhibit strong reasoning capabilities in complex tasks. However, they still struggle with hallucinations and factual errors in knowledge-intensive scenarios like knowledge graph question answering (KGQA). We attribute this to the semantic gap between structured knowledge graphs (KGs) and un...
Songze Li, Zhiqiang Liu, Zhengke Gui et al.· 0 citations
Percept-V is introduced, a dataset containing 6000 program-generated uncontaminated images divided into 30 domains, where each domain tests one or more TVPS-4 skills, and shows a weak performance of SoTA proprietary and open-source MLLMs compared to very high human performance on Percept-V.
Sam Ghosh, Ashish Goswami, Naman Agarwal et al.· 0 citations
Retrieval augmented generation (RAG) has shown great power in improving Large Language Models (LLMs). However, most existing RAG-based LLMs are dedicated to retrieving single modality information, mainly text; while for many real-world problems, such as healthcare, information relevant to queries can manifest in variou...
Saptarshi Sengupta, Shuhua Yang, Paul Kwong Yu et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This article presents multilingual deep learning models for identifying web registers -- text varieties such as news reports and discussion forums -- across 16 languages. We introduce the Multilingual CORE corpora, which contain over 72,000 documents annotated with a hierarchical taxonomy of 25 registers designed to co...
Erik Henriksson, Amanda Myntti, Saara Hellstr\"om et al.· 0 citations
Physical fidelity has received increasing attention in world models and video generation, yet how video representations encode physical information remains less understood. We introduce the World Embedding Benchmark, comprising 8,000 controlled simulation cases from 80 families spanning fluid mechanics, solid mechanics...
Yiqi Liu, Ruifeng Yuan, Yang Wang et al.· 0 citations
LLM agents increasingly screen tool outputs with small prompt-injection detectors, and teams choose among detectors by their scores on public benchmarks. We ask whether those scores predict how a detector behaves inside an agent. We replay the ground-truth tool calls of two agent benchmarks, AgentDojo and tau-bench, wi...
Biological literature retrieval systems are often developed and evaluated using broad biomedical corpora and general-purpose search tasks. However, many curated knowledge bases operate in narrower model-organism domains, where the literature is sparse and terminology is organism-specific. We introduce a retrieval bench...
Yun Wang, Gad Shaulsky, Toma\v{z} Curk et al.· 0 citations
Security workflows need models that turn complex observations and explicit policies into decisions. System One models introduced by Jev return typed predictions and probabilities; security specialization supplies the domain expertise behind those predictions. We introduce SecJev, to our knowledge the first family of Je...
Zheng Chen, Fei Yu, Haohao Huang et al.· 0 citations
Simultaneous Sign Language Translation (SLT) is critical for real-time communication, yet existing methods remain largely confined to sentence-level, offline settings that assume pre-segmented inputs. These assumptions hinder deployment in realistic scenarios involving continuous, unsegmented video streams. We present...
Si-Han Ren, Gao-Zheng Li, Yuan-Shang Quan et al.· 0 citations
A theory draws many independent observations into one framework with novel hypotheses. A researcher building such a theory must synthesize observations scattered across many papers, each describing related concepts but often in different terms. Which concepts matter most also depends on their preferences and research q...
Joseph Chee Chang, Michael D'Arcy, Amy X. Zhang et al.· 0 citations
We present a comprehensive overview of the challenges and opportunities in social bot detection in the context of the rise of sophisticated AI-based chatbots. By examining the state of the art in social bot detection techniques and the more salient real-world application to date, we identify gaps and emerging trends in...
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.
