Natural Language Processing

Google has introduced a generous free tier for the Gemini 3.1 Flash-Lite preview API, offering 15 requests per minute and 500 requests per day. Developers can obtain a free API key and configure it for tasks such as loca…

Airlines are deploying generative-AI chatbots for customer service, but booking problems persist. British Airways invested over £100 million in AI forecasting, Virgin Atlantic launched a Concierge chatbot in December 202…

Researchers propose grain calibration to validate whether large language models measure theoretical constructs correctly, not just reliably. The method decomposes constructs into clause-level components and tests each wi…

Researchers used frozen medical large language model (LLM) representations to predict primary ICD categories from both clinical narratives and structured EHR data, achieving 87.69% strict accuracy on MIMIC-IV. The multim…

Researchers introduced SCSuff, an information-theoretic metric to evaluate whether free-text explanations from large language models (LLMs) are sufficient to explain their outputs. Testing on LLMs showed explanations are…

Researchers introduced SciDraw-Bench, a benchmark for evaluating scientific figure generation by text-to-image and multimodal models, covering 32 tasks across eight figure types and ten disciplines. In a pilot study, a d…

A new audit of over twenty African NLP corpus families reveals widespread license incompatibilities, including CC-BY-SA and CC-BY-NC datasets that cannot be legally combined and NoDerivs clauses that prohibit tokenisatio…

Researchers at arXiv found that using large language models (LLMs) like GPT-5.2 to label training data for entity matching can reduce manual labeling effort by hundreds of hours, with student models performing within two…

Researchers developed a structure-preserving Marathi-to-English document translation framework using a multi-stage LLM pipeline, integrating layout-aware OCR and HTML reconstruction to maintain formatting and domain term…

Researchers introduced SEATauBench, the first agent-focused evaluation framework for Southeast Asian sovereign AI, adapting TauBench to five languages. Testing across three models revealed that English agent capabilities…

Researchers evaluated the phonological perception of deep learning models for sign language recognition, finding that pose-based models are sensitive to handshape contrasts while pixel-based models better capture locatio…

Researchers introduced a French OSCE dialogue dataset with 240 student-patient interactions and developed a controllable LLM-based pipeline to generate synthetic OSCE dialogues for clinical training. The system includes …

Researchers at the University of Oxford and other institutions found that large language models (LLMs) develop false-belief task (FBT) performance late in pretraining, dependent on model size and training volume, and imp…

Researchers propose CLOSER-VLN, a closed-loop self-verified retrieval-augmented reasoning method for aerial vision-language navigation that verifies and corrects actions before execution. The method achieves 32.01% succe…

Researchers at arXiv show that static per-layer Fibonacci spacing in sparse attention outperforms learned dilation and fixed schedules across 21 language models, achieving better perplexity and extrapolating to four time…

Researchers introduced 5ting, a system for the SemEval-2026 Task 8 (MTRAGEval) that combines BGE-M3 dense retrieval, FAISS indexing, dual-query merged retrieval, and LLM-based reranking with role-separated generation con…

A new knowledge representation architecture called Synapedia defines concepts using events sourced from Wikipedia, addressing a structural flaw in existing systems like WordNet and Wikidata. The system uses four layers a…

Andrej Karpathy declared prompt engineering dead in a June 25, 2025 tweet, introducing context engineering as its replacement. The shift redefines how developers interact with AI models, emphasizing structured context ov…

A developer built an AI tool that uses embeddings and retrieval-augmented generation to match incident alerts with runbook fixes by meaning rather than keyword overlap, closing the gap between alert messages and document…

A new survey paper on arXiv provides a comprehensive taxonomy of memory systems for AI agents, categorizing memory into forms (token-level, parametric, latent), functions (factual, experiential, working), and dynamics. T…