Natural Language Processing news and analysis on Web Pulse: 3984 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
Alibaba's Qwen2.5, a 7-billion parameter open model, runs on Android phones with 6GB RAM via Termux, enabling local multilingual AI for Indian traders and companies. It understands Hindi, English, and 20+ Indian language…
Clair, an open-source semantic news API from Serin Labs, matches news articles by meaning rather than keywords, using vector math with the bge-m3 embedding model and MaxSim algorithm to return scored, explainable results…
Paraphraser AI, a rewriting tool with controls for meaning, tone, and keywords, allows users to rewrite sentences, paragraphs, essays, and SEO content while preserving original meaning and voice. The tool supports multip…
A developer built a minimal implementation of the Lewis signaling game, where two AI agents invent their own language from scratch without any shared vocabulary. The agents achieved ~97% accuracy in coordinating to ident…
SALT, a trie-based memory-efficient LLM runner, solves the 'theme collapse' problem in long-document compression by mapping recurring themes into a keyword trie and spreading the token budget across theme branches. The s…
Team DACTYL's MCGrad model achieved a mean score of 0.974 on the PAN 2026 test set, ranking second on the leaderboard for AI-generated text detection. The researchers fine-tuned BERT-tiny models with Bayesian classificat…
A human-in-the-loop AI agent built by a Clinical and Translational Science Award (CTSA) hub drafted Translational Science Benefits Model impact summaries for 10 career-development scholars, achieving an 81.7% unanimous u…
A new arXiv preprint introduces ColGraphRAG, a late-interaction evidence retrieval method for multimodal GraphRAG that replaces single-vector bi-encoder similarity with MaxSim-style multi-vector scoring for graph-linked …
Researchers have introduced Shapley Context Pruning (SCP), a novel framework for context reranking in Retrieval-Augmented Generation (RAG) systems that applies cooperative game theory to attribute importance at the sente…
A retrospective pilot study of AI_LectureNote, a post-ASR workflow for Korean-English medical lectures, found that while the system improved English-script rendering rates from 0.39 to 0.71 on whisper-1 and from 0.26 to …
A new study from dessertlab shows that fine-tuned mid-sized open LLMs can outperform GPT baselines in schema-constrained document-level event argument extraction on the MAVEN-ARG benchmark. The approach combines role-set…
A new study from arXiv (2607.16790v1) directly compares cascaded and joint multi-task modeling for hierarchical offensive language detection, finding that a cascaded system achieves macro-F1 scores of 0.795, 0.716, and 0…
Researchers propose PPL-Factory, a task-aware and budget-aware data selection framework for large language model fine-tuning that uses perplexity-based scores to select informative training samples. Experiments on GSM8K …
A new study from arXiv introduces Symbolic Augmentation, a training-time framework that generates label-preserving augmented data to fix a structural blind spot in neural fact-checkers: their accuracy on canonical-equiva…
The NOWJ team presents adaptive pipelines for all five tasks of the COLIEE 2026 competition, including legal case retrieval, entailment, statute law retrieval, textual entailment, and judgment prediction. Their approach …
Researchers propose RIMS, a three-stage preference optimization framework for small-scale language models in retrieval-augmented generation, which uses synthetic chain-of-thought preference data and a differentiable soft…
Researchers propose DocOCR-Eval, an annotation-free framework for automatically evaluating and selecting OCR tools without ground-truth labels. The framework uses a three-stage correction and ranking strategy that aggreg…
A new study from researchers Ummugul Bezirhan, Ji Yoon Jung, and Matthias von Davier finds that multilingual sentence embeddings can replace translated English input for Linguistic-Integrated Reliability Auditing (LiRA) …
Researchers introduced EvolvingWorld, an open-schema framework for co-evolving role-play agents and world models in interactive literary worlds, addressing the limitation of existing systems that treat simulation as stat…
TalTech systems ranked first in both tracks of the Beyond Transcription Challenge (BeTraC), generating SOAP notes directly from long doctor-patient conversation recordings without intermediate transcription. The team ada…