Natural Language Processing news and analysis on Web Pulse: 5581 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
A developer at an enterprise SaaS platform restructured a conversational AI agent from a monolithic design into a modular 'skills' architecture. Each skill handles a single responsibility, such as changing a user or crea…
A developer building an AI-assisted editorial pipeline for technical writing discovered that fixing the AI reviewer required more than rubric tuning. After reordering analysis before scoring, the developer found that fai…
OpenAI released GPT-Realtime-2.1 and GPT-Realtime-2.1-mini, low-latency voice models that handle audio generation and understanding through a single model over a live connection. The mini model adds reasoning to the real…
Researchers introduced Reflexion, an AI-powered prototype for structured emotional self-reflection that integrates emotion detection, layered prompting, and metaphorical storytelling. The system guides users from emotion…
Researchers introduced Scene Graph Thinking (SaGe), a paradigm that enhances multimodal large language models by converting flat image-text data into structured scene graphs for fine-grained visual reasoning. The method,…
A controlled comparison of byte-pair encoding (BPE) and Unigram-LM tokenizers on chemistry SMILES reveals that the two algorithms build near-disjoint subword vocabularies across all 22 tested conditions, with cross-algor…
Researchers introduced BaFCo, a benchmark dataset for Bangla form comprehension comprising 200 multi-page government forms from sectors like agriculture and banking. Evaluations of multimodal large language models from C…
Researchers revisited the relation between language model perplexity and word error rate for modern end-to-end automatic speech recognition systems, finding that internal language modeling capacity and the use of neural …
Researchers introduced ResonatorLM, a new language model mechanism that replaces transformer self-attention with causal functions of damped resonators derived from physics. In a 6M parameter setting, ResonatorLM achieved…
Researchers introduced a new method for structural sequence analysis based on Algorithmic Information Theory, using the Ladderpath approach to extract nested and hierarchical repetitions. The method defines three distanc…
Researchers tested how persona prompts affect large language model agents in an iterated Split or Steal game, finding that mutual cooperation dominated in roughly 74% of rounds across 160 sessions. Model choice significa…
Researchers introduced NapMem, a framework that transforms long-term user memory into a structured action space for conversational agents, enabling active navigation across memory granularities. Trained with reinforcemen…
Researchers tested whether large language models can generate synthetic consumer data for projective techniques, finding substantial overlap with human responses in broad topics but differences in style and diversity. Th…
Researchers replaced full-corpus injection in a legal-document analysis system with two structured retrieval modes, achieving comparable accuracy while reducing token usage by up to 29.9x and costs by 25%. The study foun…
Researchers introduced SPANUQ, a lightweight probe for span-level uncertainty quantification in large language models, achieving 10-20x faster inference than sampling-based methods while outperforming them in uncertainty…
Researchers introduced the Narrative World Model (NWM), a writer-memory system that uses a narratology-grounded typed temporal-state graph and query-conditioned hybrid retrieval to answer multi-hop questions about long-f…
A new study finds that prompt robustness in large language models depends on the type of question asked, with objective questions showing different sensitivity to prompt variations than subjective belief-style questions.…
Researchers introduce Stochastic Token Steering (STS) and Stochastic Block Steering (SBS), which apply sparse autoencoder-based activation steering to only a fraction of tokens, reducing fluency degradation while maintai…
Researchers developed a vision-language framework using Low-Rank Adaptation (LoRA) on a frozen BiomedCLIP backbone to detect severe adverse events in wound monitoring. The system integrates clinical notes and wound descr…
Researchers proposed a fine-grained multimodal framework for automatic depression detection using audio-visual data, featuring a Binary Advantage-weighting Ranking Loss that optimizes latent space distribution through ha…