Natural Language Processing news and analysis on Web Pulse: 5440 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
A new arXiv paper (2609.17804v1) reports that large language models solve grade-school math word problems through a four-stage sequential pipeline — Schema Abstraction, Operation Planning, Operand Binding, and Computatio…
A systematic benchmark of open-source instruction-tuned LLMs for key-value pair extraction found that models including Gemma, Mistral, Qwen2.5, LLaMA 3, and DeepSeek approach supervised layout-aware systems on clean text…
Researchers introduced REPAIR, a self-evolving data augmentation framework that iteratively synthesizes training data to resolve long-tail concept confusion in scientific dense retrievers, according to an arXiv paper (ar…
A developer argues that IBM's promoted 'Chunkless RAG' approach, in which an AI agent navigates parsed document structure instead of retrieving fixed-size embedded chunks, is oversold for real-world production corpora. T…
David AI released DAI-S2S-ST, a single-turn speech-to-speech human preference leaderboard built on 153,000 comparative human preference ratings across 7 models, 819 distinct prompts, and 12 questions. The leaderboard ask…
Reasoning LLMs outperform standard inference at shifting Italian-to-German machine translation from binary to non-binary formulations, according to a paper by Paolo Di Natale, Laura Schlutter, Elena Chiocchetti, and Marl…
Xiaolan Xu, Sara Mendes, and Yu-Yin Hsu built a 495-sentence Chinese challenge set covering 45 occupations to measure gender bias in Chinese-to-Portuguese automated translation, testing two commercial neural machine tran…
Alina Karakanta presented a project-based translation technology module for MA Translation students that integrates large language models as translation engines, prompting and domain adaptation tools, and explainable qua…
Vincent Vandeghinste presented a paper at the 1st International Workshop on Teaching AI-Based Translation and Technologies (TAITT 2026) describing a teaching method that replicates the historical development of neural ma…
The European Association for Machine Translation published the Proceedings of the 1st International Workshop on Teaching AI-Based Translation and Technologies (TAITT 2026), held in June 2026 in Tilburg, the Netherlands. …
A study by Manuel Lardelli, published in the Proceedings of the 4th Workshop on Gender-Inclusive Translation Technologies (GITT 2026), found that neural machine translation (NMT) systems default to binary masculine/femin…
Antonio Castaldo, Johanna Monti, and Sheila Castilho published "Emotion Profiling in LLM-Based Literary Translation: Systematic Shifts Across MT and Post-Editing" in the Proceedings of the First Workshop on Style in GenA…
A study of 23 student projects in a fourth-year Machine Translation and Post-editing course found that students did not treat automatic metrics as final authority when selecting machine translation output for post-editin…
A qualitative study by Koen Kerremans, published in the Proceedings of the 1st International Workshop on Teaching AI-Based Translation and Technologies (TAITT 2026), found that a Simulated Translation Bureau (STB) in a m…
A study by Chiara Manna, Argentina Anna Rescigno, and Eva Vanmassenhove compared the automated WinoMT annotation pipeline with the instruction-tuned LLM Qwen3-8B for annotating grammatical gender in English–Italian machi…
Intel released OpenVINO 2026.4 on 16 September 2026, adding ten new model families for CPU and GPU inference, including Kokoro-82M text-to-speech, Qwen3-ASR speech-to-text, Muse Glimmer 30B, Qwen3.8 27B, Gemma 4 12B, Hy-…
A new research paper proposes "register tokens" as a method for bounded-state reasoning in masked diffusion language models (dLLMs), which generate text by iteratively denoising masked tokens with bidirectional attention…
Filippo De Simoni, an MSE Computer Science student at SUPSI, presented a 2026 bachelor thesis project on automatic parallelization of C programs that achieves speedups comparable to ad hoc parallelization with bit-identi…
A developer argues that vector similarity alone is insufficient for coding-agent memory, because a ranked list of semantically close results is not a decision about whether a past conclusion is safe to reuse. The propose…
Knowledgator Engineering released GLiFormer, a schema-conditioned encoder framework for information extraction, with two Apache 2.0 checkpoints on Hugging Face: GLiFormer Base v1 at 264.2M parameters and GLiFormer Large …