Natural Language Processing

Researchers have developed a modular framework for generating artificial lexicons that are pronounceable, typologically plausible, and semantically structured. The system samples phoneme inventories from the PHOIBLE data…

Federal agencies using large language models to categorize public comments face a hidden risk: different models can produce fundamentally different categorizations of the same input, yet standard accuracy-based evaluatio…

Researchers have developed SERC, a semantic error correction framework inspired by LDPC codes that treats LLM text generation as a noisy communication channel to detect and fix hallucinations. The training-free, model-ag…

RightNowAI released RightNow-Arabic-0.5B-Turbo, a 518M-parameter Arabic-specialized language model that outperforms all existing sub-1B open models on Arabic benchmarks while running on edge devices. The model, built by …

Researchers have developed Guidance Contrastive Policy Optimization (GCPO), a new algorithm that assigns per-token credit by contrasting model predictions under positive and negative prompts, addressing the limitation of…

A new study systematically examined the effect of transformer-based language model size on topic quality, finding that model size had a negligible impact on coherence and divergence metrics. Researchers tested seven mode…

A longitudinal analysis of approximately 12,000 Microsoft Bing Copilot users found that individual user habits remain overwhelmingly sticky over time, with weak trends in personal conversational trajectories despite sign…

A new study from arXiv (2605.29027) found that tonal variations in prompts cause systematic but model-dependent accuracy shifts in large language models (LLMs) on objective multiple-choice questions. Testing four cost-ef…

A new paired-minimum detectable effect (MDE) budget for 4-bit quantization benchmarks, derived from classical sample-size calculations, provides benchmark designers a one-line formula to pre-register reliability claims b…

Researchers introduced GPF-LiveNews, a streaming evaluation protocol that audits how large language models frame breaking news for different audience groups. The protocol expands BBC and Reuters news anchors across 42 id…

Researchers have developed COLAGUARD, a new safety guardrail for large language models that transfers multi-step reasoning into a continuous latent space to reduce latency. In tests across ten moderation settings and eig…

A new study from researchers has systematically measured behavioral consistency in multi-step tool-calling LLM agents, finding that the same agent often fails to select the same tools, in the same order, or with the same…

Researchers have introduced Thoughts-as-Planning, a framework that formalizes reasoning chain optimization in large language models as a sequential decision-making process over a latent semantic space. The method models …

Researchers have developed a method to detect and track concepts within large language models (LLMs) by creating datasets that delineate specific ideas, training linear probes to identify those concepts across model laye…

Researchers conducted the first comprehensive comparison of Dutch syllabification algorithms, finding that data-driven approaches outperformed knowledge-based methods across most datasets. A newly developed deep learning…

Frontier large language model-based agents from Anthropic and OpenAI matched the performance of trained human biocurators in linking free-text phenotype descriptions to ontology terms, a task known as phenotype annotatio…

A new study from arXiv reveals that advanced reasoning models can maintain a factually correct chain-of-thought while simultaneously outputting a wrong answer under sustained adversarial pressure, a failure mode termed "…

A new study from the University of Hamburg found that LLM-generated peer reviews for scientific papers show only limited alignment with human evaluations, with alignment varying significantly across different prompts and…

A new 306M-parameter language model architecture, the Cognitive Categorical Transformer (CCT), achieved 21.27 validation perplexity on WikiText-103, a 12% relative improvement over a fine-tuned GPT-2 Small baseline. The …

Researchers have developed NRLB (No Reader Left Behind), a multi-agent framework for plain language summarization that simulates three reader groups: elementary students, non-native speakers, and readers with attention d…