20 results for “Text Generation”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
The paper presents a new text-to-image generation model, Halcyon, that can be trained from scratch without internet-scale language pretraining.
This paper introduces a pipeline to extract grammatical rules, example sentences, and lexicons from grammar books and generates synthetic parallel corpora for fine-tuning machine translation models on…
Ziyi Cai, Shuangping Li, Yiheng Shen, Kangning Wang +1 more
This paper introduces a framework for language generation in the limit, focusing on the guarantees of validity, novelty, and output coverage.
Divya Tadimeti, Shawn Pan, Sameera Lanka, Chenghui Zhou +1 more
This paper demonstrates that targeted adaptation of the small language model Phi Silica, using dataset curation and fine-tuning, significantly improves its performance in short-form text rewriting, na…
Peihan Liu, Lucas Rosenblatt, Weiwei Kong, Natalia Ponomareva +6 more
The paper introduces ContinuousBench, a dynamic benchmark designed to rigorously test if differentially private (DP) synthetic text can genuinely transfer new knowledge and capabilities from sensitive…
Peihan Liu, Lucas Rosenblatt, Weiwei Kong, Natalia Ponomareva +6 more
The paper introduces ContinuousBench, a novel benchmark designed to rigorously test if differentially private (DP) synthetic text can genuinely transfer new knowledge, finding that state-of-the-art DP…
The paper proposes CreativeInstruct, a method to balance creativity and quality in large language models using instruction tuning and special [StartCreativity] spans.
This study systematically evaluates a wide range of chunking methods for Retrieval-Augmented Generation (RAG) to assess their effectiveness and highlight the overlooked challenges associated with chun…
The paper introduces I-WebGenBench, a framework and benchmark that converts static scientific papers into executable, interactive web systems, allowing users to dynamically explore the paper's mechani…
This paper analyzes top-tier cybersecurity papers to find evidence of generative AI's influence, finding a post-2022 increase in AI-associated marker words and a general drift toward higher lexical co…
This paper formalizes the task of generating Domain-Specific Language (DSL) code from natural language descriptions and introduces the PolkitBench dataset for evaluating LLM-based DSL code generation.
Marek Šuppa, Andrej Ridzik, Daniel Hládek, Natália Kňažeková +1 more
This paper introduces SkMTEB, a comprehensive text embedding benchmark for Slovak, and develops efficient, locally-deployable Slovak embeddings.
This paper investigates code generation for no-resource programming languages using large language models.
This paper develops a resource-aware theory of language generation in the limit under space efficiency constraints.
This paper evaluates the effectiveness of cluster-based semantic chunking compared to fixed-size and recursive chunking in Retrieval-Augmented Generation systems using the Retrieval Augmented Generati…
The paper introduces TSM-Bench, a new benchmark that demonstrates existing LLM-generated text detectors fail to accurately identify task-specific machine-generated content found in real-world Wikipedi…
Yiming Zhang, Zhonghan Zhao, Wenwei Zhang, Haiteng Zhao +12 more
This paper presents the benefits of visual pretraining for foundation model intelligence, outperforming text-only pretraining on multiple backbones and benchmarks.
The paper proposes RPSG, a method that uses private seeds and differential privacy to generate highly realistic and strongly privacy-preserving synthetic data replicas of private text for LLMs.
Yijie Jin, Jiajun Xu, Yuxuan Liu, Chenkai Xu +7 more
This paper proposes Multi-Block Diffusion Language Models (MBD-LMs) for text generation, which are obtained by post-training Block Diffusion Language Models (BD-LMs) with Multi-block Teacher Forcing (…
This paper surveys 34 peer-reviewed studies applying generative large language models to literature retrieval and eligibility screening.