BELXTR is presented, a novel embedding model based on the multi-vector (a.k.a. late interaction) architecture, which allows to leverage token-level matching information in biomedical entity linking by integrating an existing task-specific training objective and exploring active query expansion.
The results support generated memory as a selective correction to direct retrieval and highlight routing when, which, and how strongly to intervene as the central challenge.
Ming-Yuan Li, Guang-Sheng Yu, Ju-Yuan Zhang et al.· 0 citations
Arafa is introduced, a new large-scale dataset for fact-checking in Modern Standard Arabic, constructed through an automated framework leveraging large language models (LLMs) and presented a scalable approach for developing similar resources for other low-resource languages.
Christophe Khalil, Shady Elbassuoni, Rida Assaf· arXiv.org· 0 citations
We reply to the comments by M. Sienicki and K. Sienicki (arXiv:2512.07881) and by K. Sienicki (arXiv:2601.06104) on our work on quantum-mechanical statistics in human language (arXiv:2407.14924) and on quantum structure in AI-generated language (arXiv:2511.21731). We thank the authors for their careful reading and addr...
Massimiliano Sassoli de Bianchi, Roberto Leporini· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Adoption and diffusion of neologisms in online communities have received renewed attention in recent years. As internet slang terms such as APT, referring to a K-pop song, and phrases such as Canon Event meaning an embarrassing but pivotal event, go viral online, it becomes increasingly important to understand the mech...
This work introduces Qwen3.8-Omni-Flash, a natively multimodal agentic model for real-world multimodal productivity and releases Qwen-Live-Harness, an open-source framework for building responsive, real-time multimodal agents based on Qwen3.8-Omni-Flash.
We study what LLMs do when a user applies pressure in an uncomfortable situation: a user insists, begs, flatters or grieves, and the model gives up a correct fact, writes a document it should refuse, or cheers a plan that will cost the user money, a multi-turn form of sycophancy. We send frozen multi-turn scenes to 60...
Legal argument mining supports passage classification, retrieval, and argument completion. This work introduces an expert-annotated dataset of 42 U.S. federal tax opinions on corporate reorganizations under I.R.C. {\S}368. To our knowledge, it is the first expert-annotated, tree-structured argument corpus for this doma...
Luis Brena, William Jurayj, Gregory Deyesu et al.· 0 citations
The TelecomGPT-R1 family of open source unified telecom reasoning models structured around four complementary axes: protocol, knowledge, modeling, and fault are introduced, and supervised fine-tuning instills telecom knowledge and evidence-grounded reasoning patterns to overcome the cold start barrier for reinforcement...
Bo-Hao Wang, Chen-Wei Wu, Han Zou et al.· 1 citation
FineWeb-CLaR is introduced, a large-scale annotated dataset derived from FineWeb and FineWeb-2 that places web documents on a shared culture-language-region axis for corpus auditing and benchmark alignment, enabling direct comparison between corpus-side pretraining evidence and benchmark-side evaluation coverage.
Yusser Al Ghussin, Eva Gavaller, Cristina España-Bonet et al.· 0 citations
FinFIRST is the first financial benchmark to jointly evaluate answers and supporting evidence through atomic rubrics, retaining final-answer correctness as the primary objective while making the supporting research process measurable, verifiable, and diagnosable.
Ufakzeka-1, a 151M-parameter (182M with embeddings) decoder-only Turkish language model pretrained from scratch on 13.5B tokens of openly licensed text and instruction-tuned for chat, is described and three findings are believed to transfer to other small-model efforts.
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.
