Natural Language Processing news and analysis on Web Pulse: 2801 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
Microsoft has redesigned its 365 Copilot AI assistant to function as a single entry point across its apps, surfacing relevant actions based on user context. The new interface uses progressive disclosure to start focused …
The RISA development team is seeking community input on potential use cases for integrating AI into their recently launched project management tool, RISA PMT. The team has proposed several initial ideas, including automa…
Researchers have developed StoryScope, a pipeline that analyzes discourse-level narrative features to distinguish AI-generated fiction from human-written stories without relying on stylistic cues. Testing on a corpus of …
Apple will overhaul Siri and its AI tools in iOS 27, introducing a new chatbot-style Siri app, a persistent Dynamic Island interface, and a swipe-down "Search or Ask" feature, according to Bloomberg and multiple outlets.…
ADP chief economist Nela Richardson, analyzing payroll data covering one in six U.S. workers, warns that white-collar work is structurally unwinding as the historical accident that created it—driven by the internet and p…
Researchers introduced Diffinity, a training-free guidance method that enables continuous diffusion language models to satisfy formal syntactic constraints defined by regular expressions. The method constructs an analyti…
A recent study benchmarked multilingual long-context language models, finding that Polish achieved the highest accuracy at 88%, while Russian placed fifth at 84%—ahead of English at 83.9%. The research highlights how tok…
Paul Okhrem built a Retrieval-Augmented Generation (RAG) system that reduced compliance document review time from three hours to under 20 minutes per supplier package. The system automates document navigation, cross-docu…
A new critical analysis argues that human cognition is fundamentally a pattern-matching system, not a reasoning one, comparing people to "stochastic parrots" that stitch together learned linguistic sequences without true…
A developer built an AI agent workflow for the emerging charity Aura Music, using the Hermes Agent framework to automate social media content creation and monitoring. The system, hosted in a Docker container on Hostinger…
AI search systems that understand intent and context are emerging as a major SaaS opportunity, transforming how businesses access operational data. By using embedding engines and vector databases, these systems allow emp…
Seventeen publishers, including The Washington Post, Associated Press, People Inc., and USA Today Network, are licensing editorial content to enterprise customers through Snowflake's Cortex Knowledge Extensions, a moneti…
A developer built `prompt_orchestrator`, a Python module designed to manage complex LLM pipelines by structuring prompts into static, semi-stable, and dynamic sections. The tool includes configurable summarization provid…
A new study from arXiv reveals that advanced reasoning models can maintain a factually correct chain-of-thought while simultaneously outputting a wrong answer under sustained adversarial pressure, a failure mode termed "…
Researchers have developed a modular framework for generating artificial lexicons that are pronounceable, typologically plausible, and semantically structured. The system samples phoneme inventories from the PHOIBLE data…
Federal agencies using large language models to categorize public comments face a hidden risk: different models can produce fundamentally different categorizations of the same input, yet standard accuracy-based evaluatio…
A new 306M-parameter language model architecture, the Cognitive Categorical Transformer (CCT), achieved 21.27 validation perplexity on WikiText-103, a 12% relative improvement over a fine-tuned GPT-2 Small baseline. The …
A new study analyzing 17 language models from 410 million to over 100 billion parameters found that instruction-tuned systems systematically collapse linguistic entropy along discourse and structural dimensions, with mea…
Researchers have introduced Micro-Macro Retrieval (M2R), a new framework designed to reduce hallucination in large language models during long-form text generation. The system addresses the problem of factual errors by e…
Researchers have introduced Thoughts-as-Planning, a framework that formalizes reasoning chain optimization in large language models as a sequential decision-making process over a latent semantic space. The method models …