Natural Language Processing news and analysis on Web Pulse: 2430 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
CJ Olive Young, Korea's largest health and beauty retail chain, introduced AI-powered kiosks in flagship stores to assist foreign shoppers with real-time conversations in eight languages, product recommendations, and nav…
CJ Olive Young and ESTsoft launched an AI Shopping Assistant kiosk for foreign shoppers on July 8, 2026, at three Seoul stores, supporting eight languages. The kiosk uses ESTsoft's Perso Interactive avatar platform and A…
Moss launches a semantic search engine with sub-10 ms retrieval latency, eliminating the need for vector databases and enabling real-time AI applications in browser, edge, device, or cloud environments. The tool is used …
Sanity's native Embeddings feature enables semantic search in Next.js without managing external vector stores. A developer demonstrates wiring up the feature by creating an index in Sanity Studio, then querying it via a …
A developer built Zakia, a set of seven free AI writing tools for Arabic and English speakers, including an ATS resume builder and professional email writer. The tools run on Groq API, Cloudflare Workers, and GitHub Page…
Turing Award winner and Postgres creator Mike Stonebraker revealed that large language models score 0% accuracy on real-world data warehouse queries, despite achieving 80-85% on popular benchmarks like Spider and Bird. S…
AgentSkillOS released Skill Retriever, a semantic skill discovery plugin for Hermes AI agents that uses a 10,000-category taxonomy to surface relevant skills from a corpus of 1,200+ skills. The plugin runs as a pre_llm_c…
A developer at an enterprise SaaS platform restructured a conversational AI agent from a monolithic design into a modular 'skills' architecture. Each skill handles a single responsibility, such as changing a user or crea…
A developer building an AI-assisted editorial pipeline for technical writing discovered that fixing the AI reviewer required more than rubric tuning. After reordering analysis before scoring, the developer found that fai…
OpenAI released GPT-Realtime-2.1 and GPT-Realtime-2.1-mini, low-latency voice models that handle audio generation and understanding through a single model over a live connection. The mini model adds reasoning to the real…
Researchers introduced SPANUQ, a lightweight probe for span-level uncertainty quantification in large language models, achieving 10-20x faster inference than sampling-based methods while outperforming them in uncertainty…
Researchers replaced full-corpus injection in a legal-document analysis system with two structured retrieval modes, achieving comparable accuracy while reducing token usage by up to 29.9x and costs by 25%. The study foun…
Researchers tested whether large language models can generate synthetic consumer data for projective techniques, finding substantial overlap with human responses in broad topics but differences in style and diversity. Th…
Researchers introduced NapMem, a framework that transforms long-term user memory into a structured action space for conversational agents, enabling active navigation across memory granularities. Trained with reinforcemen…
Researchers tested how persona prompts affect large language model agents in an iterated Split or Steal game, finding that mutual cooperation dominated in roughly 74% of rounds across 160 sessions. Model choice significa…
Researchers introduced a new method for structural sequence analysis based on Algorithmic Information Theory, using the Ladderpath approach to extract nested and hierarchical repetitions. The method defines three distanc…
A new study finds that prompt robustness in large language models depends on the type of question asked, with objective questions showing different sensitivity to prompt variations than subjective belief-style questions.…
Researchers introduced ResonatorLM, a new language model mechanism that replaces transformer self-attention with causal functions of damped resonators derived from physics. In a 6M parameter setting, ResonatorLM achieved…
Researchers revisited the relation between language model perplexity and word error rate for modern end-to-end automatic speech recognition systems, finding that internal language modeling capacity and the use of neural …
Researchers introduced BaFCo, a benchmark dataset for Bangla form comprehension comprising 200 multi-page government forms from sectors like agriculture and banking. Evaluations of multimodal large language models from C…