Natural Language Processing news and analysis on Web Pulse: 3983 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
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…
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…
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…
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 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…
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 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 from arXiv finds that cross-lingual factual inconsistency in large language models can be mitigated at inference time, with persona prompting outperforming more invasive methods like Contrastive Activation Ad…
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 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…
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…
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 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 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 developer built a multi-agent AI data analyst on Google Cloud that converts natural language business questions into SQL queries, charts, and strategic reports, using BigQuery's public TheLook E-commerce dataset. The p…
Researchers at Huazhong University of Science and Technology and Alibaba Group's Wan Team have developed FilmWorld, a system that generates films from novels by modeling a dynamic cinematic world as a five-tuple with per…
Claude-powered scheduled tasks can automate month-end P&L reporting without servers or complex workflows, according to a guide on no-code AI automation. The system pulls financial data from sources like QuickBooks, Xero,…
Vercel's AI Gateway now supports streaming transcription in beta, allowing users to stream audio in real-time and receive transcript updates as the model produces them, reducing latency for live captioning and voice inpu…
BlueFolder launched two optional AI features on July 21st that summarize customer histories and technician notes inside its field-service platform, giving dispatchers and managers a faster way to read years of operationa…
Brad, a longtime HN user and founder, launched Orate, a native Mac app that queues selected text for on-device neural text-to-speech using AI models like Kokoro and optional Chatterbox for HD voices. The app costs $4.99 …