Natural Language Processing

Researchers propose MemSlides, a hierarchical memory framework for personalized presentation generation that separates long-term user profiles, session-level working memory, and reusable tool memory to enable stable pers…

Researchers introduced PromptMN, a pseudo-prompting domain-specific language that annotates natural language with compact typed directives to reduce context ambiguities in human-AI interactions. The language was evaluate…

Researchers at arXiv analyzed 4,434 posts and 50,338 comments from the Moltbook community to study parasocial interaction cues among autonomous AI agents. They found that attachment language, reciprocity bids, and self-i…

Researchers propose self-generated token-to-token (T2T) editing for diffusion language models, addressing a training-inference mismatch where the editor sees the model's own fluent draft errors instead of random corrupti…

Researchers introduced RAD3D-Prefix, a lightweight diagnostic-prior conditioning framework for volumetric CT report generation that keeps large language models frozen to minimize overfitting and clinical hallucination. A…

Researchers at arXiv have developed five verbalized methods to extract per-token confidence from large language models (LLMs) in machine translation, finding that these methods perform similarly to internal signals for e…

The MLLP-VRAIN research group submitted a cascaded system for the IWSLT 2026 Simultaneous Speech Translation task, using Parakeet and Qwen 3.5 models with adaptive policies. Their system achieved a +5.82 XCOMET-XL qualit…

Researchers at arXiv propose a soft prompting approach to improve language adherence in multimodal LLMs for ASR, introducing a metric to quantify violations and evaluating zero-shot prompting, supervised fine-tuning, and…

Researchers tested Word2Vec on Toki Pona, a constructed language with only ~130 words, using 1.4 million sentences. They found that non-core tokens like loanwords improved embedding quality by drawing similar words close…

Researchers introduced NarrativeWorldBench, a benchmark for long-horizon co-creative audio drama, and N-VSSM, a latent world model that outperforms frontier LLMs like Claude Opus 4.5 on long-arc consistency by 71% in a w…

Researchers at the University of Toronto introduced a novel method to evaluate second-order social bias in large language models (LLMs), where models exhibit bias in their judgments about biased content. Using a reasonin…

A study of a production enterprise LLM assistant with 110 agents and 584 tools found that routing accuracy degrades by 16-23 percentage points as the catalog scales, driven by retrieval and confusion gaps. Embedding-base…

Researchers have theoretically analyzed how deep transformers represent hierarchical structures in language, constructing models whose depth grows linearly with grammar depth and whose neuron count scales with derivation…

A comparative study of classification models within the InferBERT framework for pharmacovigilance found that domain-specific pre-trained BioBERT outperformed larger models like Med-LLaMA in detecting causal adverse drug …

A developer from Gate of AI published a tutorial on fine-tuning large language models for specialized communication tasks, using homeless shelters as a case study. The tutorial demonstrates how to structure data from the…

Oxlo.ai demonstrates how few-shot learning with large language models enables domain-specific classification without weight updates, using in-context learning to infer patterns from exemplars. The company highlights its …

SQLazy launches a deterministic SQL generation tool that lets users write complex queries step-by-step in natural language, then compiles them into auditable, production-ready SQL. The compiler guarantees no AI hallucina…

Researchers found that pruned large language models can pass multiple-choice benchmarks but fail to answer the same questions in open generation, creating a 'benchmark illusion.' The study, using multilingual question an…

A developer compares four subword tokenization algorithms—BPE, WordPiece, SentencePiece, and Unigram—used in major LLMs, explaining how tokenizer choice directly impacts inference cost, vocabulary coverage, and model beh…

A developer at the lablab Band of Agents Hackathon is building an AI-powered invoice collection system for small businesses. After identifying a gap in the market for handling overdue payments in the $2,000-$20,000 range…