Introducing multi-backends (TRT-LLM, vLLM) support for Text Generation Inference

Benchmarking Text Generation Inference

Assisted Generation: a new direction toward low-latency text generation

Lost-in-the-Middle in Long-Text Generation: Synthetic Dataset, Evaluation Framework, and Mitigation

arXiv:2503.06868v2 Announce Type: replace-cross Abstract: Existing long-text generation methods produce lengthy outputs from short inputs, leaving long-input-to-long-output generation underexplored....

Achieving Precise Text-To-Cypher Via Grounded Knowledge Graph Data Generation

arXiv:2606. 14325v1 Announce Type: cross Abstract: Property Graphs are rapidly being adopted as database frameworks for representing heterogeneous data sources.

Towards the Holographic Characteristic of LLMs for Efficient Short-text Generation

arXiv:2601. 22546v2 Announce Type: replace-cross Abstract: The recent advancements in Large Language Models (LLMs) have attracted interest in exploring their in-context learning abilities and chain-of-thought capabilities.

Open-Source Text Generation & LLM Ecosystem at Hugging Face

SCOPE: A Generative Approach for LLM Prompt Compression

SCOPE is a training‑free generative prompt‑compression framework that reduces LLM input length by chunking a prompt into semantically coherent segments, rewriting each chunk to be more concise, and then reconstructing a coherent prompt. Unlike token‑removal methods, SCOPE’s chunk‑level rewriting preserves critical information and text coherence, and includes optimization techniques for finer‑grained control of compression ratios. Extensive evaluations on question‑answering and summarization tasks show that SCOPE consistently outperforms selective compression baselines, especially at high compression ratios.

Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation

arXiv:2606.18389v2 Announce Type: replace Abstract: Large language models (LLMs) have become an effective tool for synthetic data generation, including for low-resource languages, where generated dat...

Simplifying the Modeling of Arbitrary Conditionals in Natural Language

arXiv:2606. 14943v1 Announce Type: cross Abstract: Causal Transformers model sequences through an autoregressive factorization of the joint distribution, which enables efficient left-to-right decoding and conditional likelihood computation.

FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation

FLEET is a new method for text generation that adds a memory mechanism to large language models. It represents each generation as a sparse trajectory of high‑entropy states and uses these trajectories to compute per‑token utility scores that adjust the logits. Benchmarks show that FLEET matches the accuracy of repeated sampling while being three times faster and improving accuracy on complex coding tasks, all with minimal changes to existing pipelines.

Little Brains, Big Feats: Exploring Compact Language Models

While large language models have been dominating the research landscape recently, small language models remain highly relevant across various domains; yet, they receive far less attention. In this study, we investigate how smaller language models perform during the generation stage within a Retrieval-Augmented Generation (RAG) system.

The Probabilistic Structure of Large Language Models

The paper offers a unified probabilistic framework for large language models, describing them as probability measures over token sequences defined by autoregressive conditional distributions. Training is cast as maximum‑likelihood estimation solved via stochastic gradient methods, while generation is treated as sequential simulation of the resulting stochastic process. It also explores how the asymmetry of the Kullback–Leibler divergence relates to hallucination and the distinction between plausibility and truth, and extends the perspective to diffusion models that generate data by simulating a reverse‑time stochastic process.