Natural language processing covers how machines represent, understand, and generate human language. Articles here move from foundational ideas like embeddings and attention to current research on language models, retrieval, and evaluation, written to connect the theory with the systems people use today.
Researchers from Nanjing University and Didi Chuxing built a multimodal LLM framework that reads GPS maps like a detective, consults platform regulations like a lawyer, and delivers transparent verdicts on driver-passenger disputes — hitting 88.41% accuracy while a 32B-scale baseline…
RideJudge: How an 8B Model Outperforms 32B Baselines at Ride-Hailing Dispute Resolution Read More »
GraphRAG shreds procedural knowledge into thousands of disconnected fragments. A new framework from Nanyang Technological University puts it back together — and the results in Minecraft are hard to argue with.
Researchers at the University of Maryland trained a model to teach itself — without any ground-truth labels, external graders, or verifiable rewards — by sampling multiple document-grounded reasoning traces and only distilling the ones its own internal jury agreed on.
How researchers at RPI and IBM Research taught generative LLMs to understand word senses, synonyms, and antonyms during training—without adding a single extra step at inference time—and why it consistently beats standard knowledge distillation across five benchmarks.
Every paper about detecting AI generated text eventually reports an accuracy number, and this one is no exception. The abstract says the proposed method, DGRM, boosts detection performance by up to 10.5 percent on datasets with different content and up…
DGRM: Why AI Text Detectors Collapse When Text Gets Paraphrased Read More »
A seven billion parameter model writes a clean, helpful answer, then you try to ship it. It will not fit on the phone, the latency blows past your budget, and the energy draw is not something a small product can…
ToDi: Per Token KL Divergence Control for LLM Distillation Read More »