Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2607. 21274v1 Announce Type: cross Abstract: We present CUP, a Greek book retrieval benchmark consisting of 868 catalog records and 104 expert-annotated queries with graded relevance judgments.
arXiv:2605. 25572v2 Announce Type: replace-cross Abstract: The growing complexity of quantum programming frameworks has exposed a critical limitation in existing large language model (LLM)-based code assistants: general-purpose models hallucinate PennyLane-specific gate names, misplace device configurations, and produce structurally invalid circuits when faced with specialized quantum coding challenges.
arXiv:2607. 20485v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable performance on standard benchmarks, yet it remains largely unexplored whether they truly meet user expectations.
arXiv:2607. 21324v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems increasingly employ multiple LLM agents.
arXiv:2607. 20489v1 Announce Type: new Abstract: Text-to-SQL has advanced rapidly with large language models, but complex database queries still require reasoning beyond one-shot generation, including multi-step decomposition, execution-based diagnosis, and targeted correction.
arXiv:2607. 20454v1 Announce Type: cross Abstract: All frontier large language models (LLMs) exhibit response drift -- producing outputs that deviate from expert-validated references -- yet the magnitude and structure of this drift remain uncharacterised by systematic human evaluation.
arXiv:2607. 21577v1 Announce Type: cross Abstract: Quality control in printing, particularly in rotogravure printing, still depends on slow, costly, and subjective manual inspection.
arXiv:2607. 20500v1 Announce Type: new Abstract: Large Language Models (LLMs) perform strongly on well-specified reasoning tasks with a feasible answer.
arXiv:2607. 20435v1 Announce Type: cross Abstract: Open-source LLMs (OSMs)arereaching near state-of-the-art performance, prompting prior works to trace the text they generate by embedding text watermarking algorithms directly into their weights.
arXiv:2607. 20426v1 Announce Type: cross Abstract: Existing LLM hallucination mitigation methods, including prompt engineering and model optimization, either hardly alter models'internal knowledge or have poor cross-domain generalization.
arXiv:2607. 21255v1 Announce Type: cross Abstract: Slang is a central component of everyday language, reflecting linguistic creativity, social identity, and cultural change, yet its dy- namic and non-standard nature makes it difficult to model computationally.
arXiv:2607. 21180v1 Announce Type: new Abstract: Recent advances have introduced speech-to-speech (S2S) conversational assistants capable of producing natural-sounding interactions, including non-verbal cues like tonality and mood.
arXiv:2607. 21300v1 Announce Type: cross Abstract: Machine unlearning has emerged as a tool for removing personal data from trained models to comply with recent AI regulations.
arXiv:2607. 21356v1 Announce Type: new Abstract: Fine-tuning an aligned language model on a narrow stream of bad advice can make it broadly misaligned on questions unrelated to the training data, a phenomenon called emergent misalignment.
arXiv:2607. 21273v1 Announce Type: new Abstract: Dense per-step supervision is an appealing remedy for sparse-reward, long-horizon LLM agents: reward the agent for predicting its next observation, and memory should follow.
arXiv:2607. 20553v1 Announce Type: new Abstract: Memory Manager models are pivotal in agent systems.
arXiv:2607. 20538v1 Announce Type: cross Abstract: Long-context Transformer inference increasingly relies on KV-cache compression or quantization.
arXiv:2607. 20463v1 Announce Type: new Abstract: This paper presents an AI-driven browser extension that identifies clickbait to help users avoid misleading Internet articles.
arXiv:2607. 20516v1 Announce Type: cross Abstract: Promising initial results in closed-loop large-language-model-based channel-configuration search demonstrated that neural-network widths can be optimized directly through executable code generation and accuracy feedback.
arXiv:2607. 21074v1 Announce Type: new Abstract: Fine-tuning Vision Transformers (ViTs) with low-rank adapters (LoRA) promises better communication efficiency under federated setup, yet existing aggregation strategies face fundamental limitations.