Natural Language Processing news and analysis on Web Pulse: 3964 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
A developer built two open-source packages, micromark-extension-math-extended and remark-math-extended, to let Markdown parsers handle TeX-style math delimiters (\(...\) and \[...\]) commonly emitted by LLMs. The project…
PolyAI released Dialog-RSN-1, an audio-native dialog model that processes caller audio directly, integrating turn-taking, speech recognition, function calling, and response generation into a single model while keeping te…
Researchers introduced a benchmark for reasoning over probability operators, containing 14,320 procedurally-generated English prompts across fifteen inference templates, and found that most of the 29 evaluated large lang…
Researchers propose Conditional Retrieval Alignment (CoRA), a gradient-free framework that converts a frozen encoder into a task-conditioned retriever for on-device in-context learning, using closed-form ridge regression…
Researchers propose SentiLLM, a framework that uses Semantic-Aligned Structural Abstraction to improve multimodal sentiment analysis by converting non-verbal signals into text-like tokens for large language models. The m…
Researchers introduced OVEarth-Bench, a benchmark for open-vocabulary Earth observation that expands category breadth and query diversity, finding that current methods perform limitedly, with MLLM-based methods achieving…
A new arXiv preprint (2607.27566v1) finds that direct answer-only supervised fine-tuning (SFT) on MedGemma-1.5-4B is the most robust adaptation method for multi-frame medical visual question answering on the MedFrameQA b…
Researchers developed an LLM pipeline that converts audio interviews into transcripts, maps them into the ten MADRS symptom items, estimates severity, and identifies problematic clinical ratings, achieving a correlation …
Researchers propose Generator-Gate-Corrector (GGC), a framework for reliable LLM-based Text-to-SPARQL generation, which improves query-level accuracy from 90.23% to 98.33% on MCQA while reducing inference overhead by 45%…
Researchers from an unnamed institution proposed a structured information extraction framework using LLaMA-3.1-70B to extract six semantic dimensions from financial news, finding that combining these with FinBERT sentime…
Researchers present B1ade, an efficient retrieval-augmented generation (RAG) architecture with a 335M parameter embedding model and a 1B parameter small language model (SLM). B1ade-embed achieves top MTEB scores among su…
Researchers introduced MiGUE-Bench, a benchmark for evaluating large language models (LLMs) on multi-granularity event analysis, covering tasks from event detection to future prediction. The benchmark uses an LLM-driven …
Researchers developed AWARE-FX, an auditable AI/NLP system that converts corporate annual report text into traceable firm-year hedging-disclosure measures, and tested it on 24,909 Hong Kong firm-years from 2008 to 2025, …
Researchers propose DualAnchor, a gloss-free sign language translation framework that preserves language priors and improves lexical fidelity, achieving strong performance on PHOENIX-2014T and CSL-Daily. The framework us…
A developer built EasyStock, an AI assistant that converts natural-language queries into stock screening criteria, fetching market data and providing explainable results. The tool aims to simplify stock screening by allo…
Betocmn released Widen, an open-source (MIT) native Mac app built with Swift that serves as a Postgres GUI with text-to-SQL capabilities, supporting local or cloud LLMs via OpenRouter or Apple's on-device model. The app,…
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…