Natural Language Processing news and analysis on Web Pulse: 3968 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
Researchers Ivan Martinez-Murillo, Robiert Sepúlveda-Torres, and Juan Pablo Consuegra-Ayala found that transformer-based fraud detection models trained only on English achieve near-perfect in-language performance (F1 ≈ 0…
ElevenLabs has introduced Expressive Mode, a feature within its ElevenLabs Agents platform that adds emotional tone and inflection control to real-time voice agents, allowing them to sound annoyed, amused, sarcastic, or …
Researchers Bruno Franco and Edson Scalabrin introduced Compositional Graph Similarity (CGS), a graph-based metric for evaluating Transformer models on the ReCOGS benchmark, and found that the lowest-scoring categories a…
Koharu Saeki and Daisuke Bekki from Ochanomizu University introduced Express, a web-based interactive development environment for the Japanese automated inference system lightblue, which shifts grammar development from e…
Researchers Chit-Fung Lam and Elaine Uí Dhonnchadha presented the development of Cantonese and Irish treebanks within the Parallel Grammar (ParGram) Project at the Third Workshop on the Bridges and Gaps between Formal an…
Researchers Nanako Miyagawa, Hinari Daido, and Daisuke Bekki introduced Neural Wani, an integration of a lightweight LSTM-based neural model into the automated theorem prover wani for Dependent Type Theory, achieving a 1…
Researchers Artem Saloev, Erin Pacquetet, and Nicolas Ballier found that the ABX experiment with Mimi's semantic token codebook fails to capture the mapping of semantic tokens to phone realisations, but by realigning Mim…
Rui Sousa-Silva, in a paper presented at the Second International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security (NLPAICS) in Alicante, Spain, in June 2026, found that forensic l…
Judith Sieker and Sina Zarrieß, in a position paper presented at the Third Workshop on the Bridges and Gaps between Formal and Computational Linguistics (BriGap-3) in Paris, France, in July 2026, argue that misalignments…
A study by Yan Cong and Julia Rayz, presented at the Third Workshop on the Bridges and Gaps between Formal and Computational Linguistics (BriGap-3) in Paris, France, in July 2026, found that current vision-language model…
Priscilla Adenuga's paper, presented at the Second International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security (NLPAICS) in June 2026 in Alicante, Spain, argues that prompt inje…
Northeastern University scientists from the Neural Dynamics Group developed eGoT (enhanced graph of thoughts), an algorithm that teaches large language models to connect information across biomedical domains and produce …
Encore AI announced a $30 million Series A on July 29 led by Team8, Planven, and The Garage, with participation from Lukatz and several bank and insurer customers, to expand its enterprise customer-interaction platform t…
Gradium, the voice AI developer led by CEO Neil Zeghidour, opened a public beta on July 30th for a text-to-speech model designed to pronounce phone numbers, email addresses, IBANs and time expressions without preprocessi…
Apple's new Siri AI, arriving in iOS 27, is now available via public beta on iPhone 15 Pro, iPhone 15 Pro Max, any iPhone 16 model, or any iPhone 17 model, with a stable release expected in September. The update introduc…
Telnyx released a Python Flask example that uses AI to classify voicemails and route them to appropriate workflows such as Slack alerts, email, or ticket queues. The app transcribes audio voicemails, then uses Telnyx AI …
Seedance 2.5, the next version of the Seedance AI video platform, will support up to 50 media inputs in a single creative task, including 44 images, three video clips and three audio files, enabling multimodal workflows …
An engineer at an ISP built a WhatsApp billing assistant using Corrective RAG (CRAG) and found that the main challenge was not retrieval but the model narrating correct numbers incorrectly. The system uses hybrid retriev…
Retrieval Augmented Generation (RAG) improves AI accuracy by having the model search a knowledge base for relevant facts before generating answers, reducing confident hallucinations. A developer explains that RAG works l…
Vector embeddings represent data as coordinates in a high-dimensional space, capturing relationships between items based on context. Spotify uses this technique to power its recommendation engine, placing songs with simi…