Natural Language Processing news and analysis on Web Pulse: 5610 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
Klarna's 2024 announcement that its AI agent replaced 700 human agents backfired when customer satisfaction dropped, forcing the company to rehire in 2025. CEO Sebastian Siemiatkowski acknowledged the company pushed too …
A writer argues against changing their long-form writing style to short-form content due to AI and shrinking attention spans, asserting that long-form writing retains value and that writers should maintain their unique v…
The Seoul Metropolitan Office of Education announced Monday it will expand college and career-admissions support for migrant-background students, including AI-powered simultaneous interpretation for families with limited…
QuantVectors, a data company specializing in document training datasets for AI and OCR models, is seeking annotated Indic document datasets in languages such as Hindi, Marathi, and Tamil. The company is looking for docum…
NagMeLater is a WhatsApp-based reminder and to-do list service that uses AI to parse natural language commands in multiple languages. Users can set reminders and tasks by sending plain text messages to the bot, which the…
A developer built a Hybrid RAG system combining FAISS for dense vector search and BM25 for keyword search, fused via Reciprocal Rank Fusion, orchestrated with LangGraph and Claude Sonnet, and deployed with a Streamlit UI…
A developer in Bahía Blanca, Argentina built CHE MCP, the country's first national MCP ecosystem that connects AI agents to 80+ official Argentine data sources through a single server. The system uses a 5-stage classifie…
Developer Lenn Voss introduces Recall, an open-source tool that uses classical NLP algorithms like TF-IDF and TextRank to summarize Claude Code sessions locally, bypassing expensive LLM calls and cloud dependencies. The …
A developer built MemeFinder, a native macOS app that enables semantic search of local meme collections. The app uses OCR and vector embeddings to index memes, and allows users to search and copy memes to clipboard via a…
A developer identifies the 'index distribution problem' as a fundamental flaw in agent-based search systems, where retrieval indexes encode past relevance judgments rather than semantic truth, causing agents to produce c…
RealPact, a Y Combinator Summer 2026 company founded by Dartmouth students, has launched voice-powered AI agents that automate real estate transactions by retrieving property records, filling contracts, and managing work…
Researchers introduced CoLabScience, a proactive AI assistant that uses a reinforcement learning framework called PULI to autonomously intervene in biomedical research discussions. The system, trained on a new benchmark …
Researchers at Northwestern University and the University of Chicago developed a computational method to measure open codes in qualitative analysis, using LLM-enriched hierarchical clustering and four novel metrics (Cove…
Motley AI achieved a 75.3% pass rate on the BIRD-INTERACT benchmark using the Claude SDK and its open-source semantic layer SLayer, far exceeding the official best of 36.33%. The agent harness provided the biggest improv…
OpenAI has launched ChatGPT Scheduled Tasks, a feature for Plus, Pro, and Team subscribers that automates recurring prompts such as daily news briefings and email summaries. Users can set tasks to run at specific times w…
Researchers Bhavik Chandna and Procheta Sen introduced a counterfactual explanation framework for retrieval models that identifies which terms need to be added to a document to improve its ranking, addressing why a docum…
Researchers at ACL 2026 found that entropy collapse in LLM reasoning, which undermines test-time scaling, is driven by premature overconfidence at a small set of critical tokens. They proposed SCOPE, a method that applie…
Researchers at the Association for Computational Linguistics introduced a Dual-Phase Self-Evolution (DPSE) framework for large language models that jointly optimizes user preference adaptation and domain-specific compete…
Researchers introduced TRuST, a large-scale dataset with ~300k annotations for toxicity recognition, unifying prior resources through a synthesized definition. Benchmarking showed fine-tuned PLMs outperform LLMs on toxic…
Researchers at the 64th Annual Meeting of the Association for Computational Linguistics introduced a dual-task paradigm combining arithmetic and sentence comprehension to study how language models allocate cognitive reso…