Natural Language Processing news and analysis on Web Pulse: 2503 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
Logistics startup Chain launched an AI-powered Autopilot Booking Agent that automates carrier outreach, rate negotiation, and booking for routine freight, aiming to free brokers from repetitive tasks. The tool works with…
Elevenwritt, an AI tool, launched a LinkedIn post generator designed to help professionals and B2B creators build their brand by generating high-performing content. The tool uses specific formats like story posts and con…
A developer built a free technical checker that evaluates whether a website is ready to be crawled, understood, extracted, and trusted by AI-powered search engines. The tool separates 'AI visibility' from 'AI readiness,'…
Google has launched Vids, an AI-powered video creation and editing tool integrated with Gemini, enabling users to generate storyboards, scripts, and video clips from prompts. The tool offers features like screen recordin…
Researchers introduced Patent-CR, the first English dataset for patent claim revision, containing rejected and granted patent claims. Evaluating large language models, they found GPT-4 performed best but still fell short…
Researchers introduced FlowPlan-G2P, a graph-mediated framework that transforms scientific papers into patent descriptions through concept graph induction, section-level planning, and graph-conditioned generation. The sy…
Researchers at the 2025 Conference on Empirical Methods in Natural Language Processing introduced PatentScore, a multi-dimensional evaluation framework for LLM-generated patent claims. PatentScore integrates hierarchical…
Researchers at Arizona State University argue that calling intermediate tokens generated by language models 'reasoning traces' or 'thinking traces' anthropomorphizes the models and misleads users about their capabilities…
A developer working on AI voice for small businesses highlights the gap between controlled AI demos and messy real-world phone calls, noting that real-world deployment often disappoints.
Fivy launches an AI-powered review management platform for small businesses, automatically monitoring Google reviews, drafting replies, and providing weekly sentiment insights to help improve reputation and customer expe…
A developer built a free AI grammar checker that runs entirely in the browser, using DeepSeek's API for grammar checking and local computation for readability stats. The tool, called AI Grammar Checker, costs under $2 pe…
Researchers from Microsoft Research, UC Berkeley, UC San Francisco, and Columbia University developed generative causal testing (GCT), a method that distills black-box brain-prediction models into testable verbal explana…
Supercomplete.ai launches an AI writing assistant that provides instant answers with sub-0.5 second response times, works across all platforms, and adapts to user style over time. The tool offers free and pro tiers, targ…
Researchers introduced CRISP, a new evaluation paradigm that diagnoses visual spatial intelligence in vision-language models by measuring consistency between implicit perception and explicit reasoning. The study found th…
New research from arXiv reveals that larger language models consistently outperform smaller ones on reasoning benchmarks by an average of 6-7%, with the key advantage being constraint-guided reasoning—the ability to iden…
Researchers introduced HierBias, a hierarchical context-conditioned media bias detector that models document context to improve sentence-level bias classification. The system achieved 0.853 F1 and 0.723 MCC on BABE and B…
Researchers found that applying Nonviolent Communication constraints to large language models reduces conversational escalation in conflict-prone dialogues, improving trustworthiness without requiring extensive retrainin…
Researchers introduced NEST-V1, a multimodal framework that generates emotion-conditioned Nepali Sign Language avatars from spoken words, achieving 81.1% ASR accuracy and 79.21% emotion recognition accuracy on a dataset …
Researchers developed a methodology to transform Hindi WordNet into 1.25 million instruction-response pairs, fine-tuning a 12B-parameter language model to create a specialized conversational AI for low-resource languages…
Researchers present the first systematic survey of unified vision-language perception in Multimodal Large Language Models (MLLMs), tracing the paradigm evolution through a five-stage taxonomy and identifying open challen…