Natural Language Processing news and analysis on Web Pulse: 5539 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
A new open-source MCP server called talkthrough-mcp, released under the MIT license, lets developers turn narrated screen recordings into structured data for AI agents without any cloud dependency. The tool runs locally …
Sperm whales off the coast of Dominica shorten their click sequences and increase use of certain vowel-like sounds when ships are nearby, according to a study published today in Ecological Informatics by Project CETI. Th…
A study by AN found that providing a get_template_view tool eliminated the visibility-clause tax in outline views, raising anaphora success to 45–48 out of 48 with near-zero asks across four arms, three models, and 1,728…
Axon's AI-powered police report writing tool, used in over 600,000 reports, introduces factual errors that officers must spend time correcting, according to public records obtained by Forbes. The errors, which include mi…
A developer explains that an LLM's context window is the total number of tokens it can process at once, and that exceeding this limit causes older information to be forgotten. The post also covers retrieval-augmented gen…
Substack launched an AI detector powered by Pangram to scan posts and comments for AI-generated text, but the tool inherits the same blind spot as earlier detectors like DEV.to's 'Sloan': it flags well-written, structure…
A software developer has created a global system prompt to force conversational AI coding agents to stop simulating human conversation and output machine-style responses, citing the anthropomorphic interface as an HCI di…
Researchers introduced MIRA-Ev, a clinical argument mining benchmark built on Spanish MIR licensing-exam cases, re-annotated by expert clinicians with span-level premises, claims, and directed support/attack relations, a…
Researchers propose SAGE (ScAffolded Generative models for Explanation), a neuro-symbolic framework combining language models with cognitive models for pragmatic reasoning, achieving high accuracy across three case studi…
Researchers present AutoJourn, a system for multi-perspective news generation and bias-aware evaluation using large language models, that extracts diverse perspectives from social media, generates balanced summaries, and…
A new survey from arXiv (2607.19011v1) finds that multimodal humor in memes, cartoons, and comics remains difficult for AI systems because intended meaning depends on non-literal mechanisms, shared cultural knowledge, an…
Researchers propose RLAES, a unified LLM framework that jointly optimizes automated essay scoring and feedback generation through reinforcement learning, achieving the best scoring performance among LLM-based methods on …
A new study evaluating Vision-Language Models (VLMs) for safety reasoning finds that these models frequently misinterpret anomalous scenes as hazardous, revealing an over-reliance on contextual irregularity rather than t…
A rationale-guided knowledge distillation framework for cross-lingual stance detection outperforms competitive baselines on multilingual benchmarks, according to a new arXiv preprint (2607.18693v1). The method uses Chain…
A new study from researchers using LLaMA and Mistral models finds that instruction-tuned Transformers encode discourse relations such as causation and antithesis asymmetrically across layers, with early layers making pre…
A new study introduces LatentMT, the first systematic application of latent-reasoning looped language models (LoopLMs) to machine translation, achieving performance comparable to models three to five times larger using a…
A new study introduces the Artificial Intelligence for Indian Legal Question Answering (AILQA) system, which uses embedding and generative models including large language models to improve legal question answering for th…
A new study from researchers at the University of Zurich finds that reinforcement learning with verifiable rewards surpasses supervised fine-tuning for legal neural machine translation, though enhanced small models still…
A new training-time framework called Dependency-Aware Intermediate QA Supervision (DAIS) improves final-answer accuracy on complex reasoning tasks by converting filtered teacher rationales into stage-level QA records tha…
A new study from arXiv (2607.18321v1) provides empirical evidence that the human brain's N400 response to next-word predictability during reading differs significantly between content words and function words, with verbs…