Latest AI/ML News
2784 articles · arXiv cs.CL
arXiv:2609.27773v1 Announce Type: new Abstract: As Large Language Models (LLMs) move from conversational assistants to advanced agentic systems, guard…
arXiv:2609.27770v1 Announce Type: new Abstract: Autonomous web agents, powered by Large Language Models (LLMs), have garnered significant attention fo…
arXiv:2609.27758v1 Announce Type: new Abstract: Safety alignment in large language models is trained primarily in English, and recent work reports tha…
arXiv:2609.27717v1 Announce Type: new Abstract: Human-written agent skills encode rich workflows for real-world problem solving, but are typically use…
arXiv:2609.27690v1 Announce Type: new Abstract: Researchers in industry and academia use synthetic survey respondents powered by large language models…
arXiv:2609.27678v1 Announce Type: new Abstract: Contract inference requires multiple judgments about a shared document, but aggregate accuracy can con…
arXiv:2609.27669v1 Announce Type: new Abstract: Small language models (SLMs) are increasingly paired with knowledge graphs (KGs), yet end-to-end KG qu…
arXiv:2609.27650v1 Announce Type: new Abstract: Brain-to-language decoding translates neural activity associated with language production, internal sp…
arXiv:2609.27607v1 Announce Type: new Abstract: An AI-generated radiology report can resemble a physician's report while omitting an abnormality, addi…
arXiv:2609.27603v1 Announce Type: new Abstract: In-Context Learning (ICL) has become a cornerstone of modern LLM deployment. However, existing ICL pos…
arXiv:2609.27590v1 Announce Type: new Abstract: Long-context evaluations often test whether a model can recover distant evidence, but recoverability d…
arXiv:2609.27558v1 Announce Type: new Abstract: Studying syntactic patterns in naturally occurring language requires a large parsed corpus, but manual…
arXiv:2609.27510v1 Announce Type: new Abstract: Modern large language models are pretrained on massive datasets, making it difficult to prevent benchm…
arXiv:2609.27418v1 Announce Type: new Abstract: Systematic reviews underpin clinical guidelines, yet their data-extraction step is a major expert-labo…
arXiv:2609.27396v1 Announce Type: new Abstract: DSpark-style parallel drafters have made speculative decoding highly effective, yet their draft phase…
arXiv:2609.27395v1 Announce Type: new Abstract: Compact vision-language models (VLMs) now power a growing share of multimodal applications. The benchm…
arXiv:2609.27387v1 Announce Type: new Abstract: AraGenre is a shared task on hierarchical, definition-guided Arabic genre classification, motivated by…
arXiv:2609.27380v1 Announce Type: new Abstract: Likelihood-based context compression can account for cross-context redundancy through sequential scori…
arXiv:2609.27376v1 Announce Type: new Abstract: Cross-lingual legal question answering must retrieve statutes across languages while preventing unsupp…
arXiv:2609.27374v1 Announce Type: new Abstract: Test-time scaling with parallel branches is widely adopted to improve performance on challenging reaso…