Natural Language Processing news and analysis on Web Pulse: 2585 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
Ferrix has launched a suite of AI agents designed specifically for product managers, automating repetitive tasks such as customer feedback analysis, product discovery, validation, opportunity planning, PRD generation, sp…
A developer built a groundedness-checking layer for a local RAG system to catch hallucinations, running on Ollama with an 8B model. The layer decomposes answers into claims and verifies each against source passages, catc…
A developer built an evidence-bound AI report system for YouTube comments that ties every claim back to specific source comments. The system uses an 'EvidenceBoundClaim' data structure linking each summary claim to the c…
Researchers propose SPSD, an edge-based pipeline that compresses user prompts using a small language model before sending them to a cloud LLM, reducing input tokens by an average of 99.9 per call while maintaining respon…
FocusOnFun team's Vortex system achieved 90.5% in the Preliminary Round and 'Excellent' overall performance with 'Outstanding' QA results at the Ho Chi Minh City AI Challenge 2025. The multimodal video retrieval system i…
Researchers propose QueryGaussian, a training-free framework for open-vocabulary 3D instance retrieval that decouples semantic understanding from geometric representation, enabling efficient retrieval in city-scale scene…
A systematic experimental analysis of eight state-of-the-art Diffusion Language Models (DLMs) across eight benchmarks reveals that generation-time design choices strongly influence performance and computational efficienc…
Researchers propose REVEAL++, a differentiable phenotypic grouping method for vision-language retinal modeling that improves Alzheimer's disease risk prediction by treating phenotypic similarity as a continuous, learnabl…
Researchers introduced a prompt-based uncertainty decomposition method that separates action confidence from request uncertainty, enabling LLM agents to proactively seek clarification when task specifications are ambiguo…
Researchers introduced GLARE, an LLM-based natural language interface that translates user questions into SQL queries over local explanation data to provide global explanations for black-box image classifiers. The system…
Researchers introduced TreeTracer, a visual analytics tool that aggregates hundreds of stochastic LLM generations into syntax-aligned trees to expose hidden biases. The tool uses perturbation analysis and contrastive inf…
Researchers developed an ensemble of large language models, including Google's Gemini and Gemma, to automatically identify EQ-5D health-related quality-of-life studies in PubMed from abstracts. The weighted ensemble achi…
A study fine-tuning seven large language models on Arabic found no evidence of Semitic-specific cross-lingual transfer; gains were driven by task-format alignment rather than linguistic relatedness.
Researchers have identified and characterized positional bias in in-context learning for diffusion large language models (dLLMs), showing that query placement significantly affects generation quality. They propose Averag…
Researchers introduced the Argent Signaling Protocol (ASP) to mitigate semantic drift in multi-agent LLM systems by attaching structured quality signals to AI responses. In tests, ASP improved pass rates on a document-gr…
Researchers at the Allen Institute for AI used training-data attribution to map which regions of the pretraining corpus support social-reasoning versus STEM-reasoning in the OLMo3-7B language model. They found that socia…
Researchers at the University of Washington and Allen Institute for AI conducted the first fine-grained study of narrative features in Dolma, a 3-trillion-token open LLM pretraining corpus. They developed NarraBERT, a Ro…
A new human-in-the-loop pipeline measures how completely a computer science program covers international curricular guidelines, applied longitudinally to one accredited BSc program against CS2013 and CS2023. The program …
Researchers proposed LUCID, the first hallucination detection method for large language model-based knowledge graph reasoning, which jointly leverages LLM attention scores, KG semantics, and structural information. Exper…
Researchers introduced MiqraBERT, a Sentence-BERT model finetuned from AlephBERT for detecting verse-level semantic similarity in Biblical Hebrew. The model improves distributional separation 2.7-fold over the pre-traine…