Natural Language Processing news and analysis on Web Pulse: 5481 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
Airtxt, a new dictation app priced at $9, claims to undercut Wispr Flow's $15 subscription while offering on-device or cloud processing, meeting transcription, and keyboard integration across all apps. The app's website,…
Towards Data Science reports that row-level chunks, where each body row of a table is paired with its column headers, can serve as the unit of retrieval in retrieval-augmented generation (RAG) systems, often returning th…
Pythonaibrain-NLP 0.2.0, a structured NLU/NLG framework for Python, is now available on PyPI and GitHub. The framework separates understanding, dialogue state, retrieval, and generation into explicit components, using a …
VLM Run, founded by CEO Sudeep Pillai, launched an OpenAI-compatible gateway on August 19 that routes document-processing work across six open OCR and vision-language models, including GLM-OCR, DeepSeek-OCR-2, dots.mocr,…
Video to Prompt, a free AI tool, generates editable English prompts from short videos or YouTube Shorts links, extracting visual style, subject, action, lighting, camera movement, and audio cues. The free tier allows 1 a…
Researchers present SNAIL, a hybrid named entity recognition framework that automatically identifies bioinformatics software and database names in biomedical texts, outperforming existing methods including bioNerDS2, Cha…
Researchers from an unnamed institution report that a contrastive decoder can extract open-vocabulary word-level information from non-invasive EEG during silent reading, achieving reliable above-chance word-grouped top-1…
A new arXiv preprint (2608.19299v1) reports that large language models can generate operationally realistic air traffic control transmissions, but only with lightly constrained prompts and in-context examples. In experim…
A new arXiv study (2608.19558v1) finds that confidence rankings for financial named entity recognition (NER) change under domain shift, with whole-output probability being the strongest in-domain error detector but deter…
A virtual assistant called ATHENA, developed for the Society of Petroleum Engineers, improved productivity and performance equality among 75 professionals on well-planning tasks compared to a state-of-the-art RAG baselin…
A study submitted to arXiv on 2 Jun 2026 compares transformer models BERT, RoBERTa, and BART for text summarization, examining their architectures, pretraining strategies, and suitability for extractive and abstractive t…
A new study from arXiv (2608.19211v1) finds that four audio-language models preserve prosodic information in their audio paths and late LLM states but fail to express it in final responses, with targeted hidden-state int…
Cosine similarity, the default metric in most RAG pipelines and vector databases, discards vector magnitude, which can carry critical semantic information such as confidence, specificity, or negation, leading to failures…
A developer used AI-assisted coding to build a client-side Keyword Density Analyzer that runs entirely in the browser, addressing privacy concerns with third-party SEO tools. The tool leverages regex sanitization and pur…
Shopify Engineering implemented gisting to compress the Sidekick GraphQL agent's system prompt from ~6,000 tokens to ~1,500 gist tokens (a 4:1 reduction) without losing prediction quality, cutting median time to first to…
Between 16th and 20th August, OpenAI replaced ChatGPT's search tool call from JSON to a compact query language with freshness windows, domain targeting, and verticals for products, places, images, and widgets, as observe…
Pipe Language released pipe-docs, a semantic search and RAG MCP server that turns documentation and Go/Pipe source code into a searchable index for AI IDEs, offering seven tools with zero dependencies and published on th…
Hume AI's new research introduces three tests to quantify benchmark optimization in speech recognition, finding that several of 11 open-source ASR models reproduced benchmark transcripts from VoxPopuli and LibriSpeech ev…
OpenAI's ChatGPT search now uses the site: operator at scale, allowing users to restrict search results to specific domains, as announced by Simon Willison on his Weblog on August 20, 2026. This enhancement improves the …
A technical blog post outlines a pipeline for analyzing political communications using AI, including PII stripping with Presidio, embedding with mixedbread-ai/mxbai-embed-large-v1, fine-tuning a DeBERTa-v3-large classifi…