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 training-free framework combining reasoning and retrieval over Wikipedia improves multilingual multimodal entity linking by 6.9% overall and up to 23.3% on rare-entity slices on the MERLIN benchmark, according to an ar…
A new arXiv paper (2609.11699v1) introduces Negative Self-Distillation (NSD), a framework that improves large language model reasoning by diverging from self-generated flawed reasoning rather than imitating privileged gr…
A prompt-based approach to minimal-edit grammatical error correction reached an F0.5 score of 78.32 on the BEA-2019 test set, closing the gap to the fine-tuned single-model state of the art (Staruch et al., 2025) to 0.38…
A new arXiv paper (2609.10923v1) introduces "Structurally Speaking," a lightweight structured prompting protocol that guides large language models to translate between explicit graph connectivity and motif-level abstract…
Researchers introduced a completeness estimation approach for multimodal sentiment analysis that quantifies how much sentiment-relevant information survives in incomplete data and uses that estimate to guide reconstructi…
Researchers introduced CMNIE, an information extraction benchmark for Chinese military news containing 13,000 instances drawn from public Chinese military news and manually annotated for 7 event types, 10 argument roles,…
A study of five realistic noise conditions applied to 3,822 stereotype-related responses found that surface noise in text — typos, informal spelling, and broken punctuation — makes large language model judges far more li…
A study of 93 Urdu stories generated by three contemporary LLMs — GPT-5.1, Qwen-3-Max, and DeepSeek-3.1 — found that the models frequently make basic grammar and semantic errors, produce incoherent and repetitively unnat…
A new arXiv paper (2609.10934v1) reports that modeling semantic uncertainty — an LLM-derived measure of how strongly a turn so far constrains what may plausibly come next — substantially outperforms prompt-based and fine…
A new arXiv paper (2609.10792v1) tests whether transformer-based models internalize the same linguistic features as traditional feature-based classifiers in Automatic Readability Assessment across Arabic, English, French…
A new arXiv paper (2609.10830v1) reports that language models' apparent memory of training data is largely confounded, using exact duplication counts from the published pretraining corpora of OLMo-2 and Pythia. Across fi…
A new arXiv paper (2609.11022v1) introduces a controlled benchmark testing whether vision language models can decide when to answer a physical reasoning question immediately versus when to select the cheapest additional …
A developer outlined a multi-stage pipeline for how modern AI agents select and execute tools, covering intent analysis, semantic tool matching, and execution chaining. The writeup details performance trade-offs across s…
A developer built a court outcome prediction system that reduced target leakage from 92% to 0.1% across 609,715 Dutch court rulings by stripping outcome-announcing sentences before training. The system uses a traceable L…
A developer published a tutorial for building a Medical RAG system that parses personal medical PDFs with Unstructured.io, stores embeddings in Pinecone, and cross-references queries against the PubMed API via LangChain …
Manticore Search released version 29.9.0, adding chunked auto-embeddings that let long documents store multiple vectors instead of one, with five chunking strategies including truncate, mean, fixed, recursive, and senten…
Researchers Vasileios Baltatzis, Mert Inan, Connor Gillis, Raja Kushalnagar, Lorna Quandt, Leah Findlater, and Colin Lea introduced DiscoSign, a modular Large Language Model-based framework for discourse-aware text to si…
A September 11, 2026 arXiv paper (2609.12303) reports that distilled byte-level transformer models with roughly 1 billion parameters eventually surpass token-based models of the same size, reaching a higher downstream pe…
GPT-Live-1, a new full-duplex voice API, is now available to developers at $0.05 per minute, allowing the model to listen and speak simultaneously and detect user interruptions in real time. The model scored 80.1% on int…
NASA's Marshall Space Flight Center Impact AI team and IBM Research released INDUS-SDE, a specialized language model pre-trained on NASA's Science Discovery Engine data that reached 78.1% top-1 masked language modeling a…