Natural Language Processing news and analysis on Web Pulse: 2605 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
Respond.io, a Kuala Lumpur-based customer conversation management platform, raised $62.5 million in Series B funding led by Camber Partners with participation from Endeavor Catalyst. The company reports $35 million in an…
A University at Buffalo student was falsely accused of AI cheating after Turnitin's detector flagged his original work as AI-generated. Universities including Vanderbilt, MIT, and the University of Iowa have disabled or …
Naver researcher Claudius, maintainer of LispE and TAMGU, discusses his career in symbolic AI and computational linguistics, including his work on the Xerox Incremental Parser and the limitations of rule-based language s…
An A/B test by DataForge on a Fashion Retail database found that adding a semantic layer improved LLM-generated analytical answer quality by 19%, from 7.27 to 8.67 out of 10. Without semantic context, models made mistake…
Amazon Web Services announced the general availability of Web Search on Amazon Bedrock AgentCore, a fully managed tool that enables AI agents to ground responses in current, cited web knowledge without data egress from c…
A developer built a local RAG pipeline using Ollama, ChromaDB, and TinyLlama for private PDF Q&A, then exposed it as an MCP server so Cursor IDE can query documents directly. The project uses sentence-transformers all-Mi…
Hunar.AI has deployed voice AI agents to automate frontline hiring, powering over 500,000 calls daily for enterprises including Swiggy, Zepto, Croma, and Starbucks. The platform connects over 2 million candidates per mon…
Agentic QA pipelines are replacing script-based test automation in 2026, as teams shift from maintaining explicit test instructions to describing goals. Quash's 2026 State of QA Automation Report found that teams spendin…
A developer ran tests comparing AI companion behavior across models and relationship architectures, finding that a cheaper model with relationship architecture behaved more like a person than a stronger model with a stat…
Researchers Ankit Bhattacharjee and Krityapriya Bhaumik introduced the Robust Dual-Signal (RDS) Fusion framework, a hybrid neuro-symbolic gating architecture for irony detection in social media text, achieving 78.1% accu…
A translator working on an AI safety awareness flyer for schools in northern Nigeria found that key terms like 'deepfakes' and 'prompt' have no direct equivalents in Hausa, forcing approximations that risk losing meaning…
A developer compared two AI meeting note-taking tools, Otter and Granola, and found they represent opposite design philosophies: Otter transcribes everything and then summarizes, while Granola enhances user-typed notes w…
A developer ported the DocNest document-chunking engine from Python to idiomatic C#/.NET 8, eliminating the need for a Python sidecar in .NET RAG stacks. The engine preserves document structure (headings, tables) to prev…
A user training a T5 model asked for alternative metrics to Exact Match for evaluating text generation. Community members suggested ROUGE-1, ROUGE-2, and BLEU, and recommended Braintrust for running evaluations on small …
A developer outlines a blueprint for building a natural language query interface for databases using LLMs. The system architecture includes schema retrieval via RAG, prompt assembly, SQL generation, validation, and safe …
Researchers introduced disagreement-based cross-model routing for implicit video question answering, achieving a +1.43 AvgAcc improvement on the ImplicitQA benchmark by routing disputed questions from Gemini 3.1 Pro Prev…
Researchers developed FUSE, a Bayesian framework that quantifies aleatoric and epistemic uncertainty in vision-language models, achieving state-of-the-art uncertainty calibration for downstream applications like robotics…
Researchers introduced GridVQA-X, a diagnostic framework to evaluate cross-modal explainability in Vision-Language Models. The framework uses synthetic data with ground-truth explanations to test whether explainability m…
Researchers introduced MMLongEmbed, the first comprehensive benchmark for evaluating multimodal embedding models in long-context scenarios. The benchmark includes four retrieval tasks across text, document, and video mod…
Researchers introduced the Membership Inference Test (MINT) Demo 2, a framework to detect whether specific data were used in training machine learning models, achieving up to 90% accuracy in tests on face recognition mod…