Related papers: R2D2: Robust Data-to-Text with Replacement Detecti…

In Natural Language Generation (NLG), important information is sometimes omitted in the output text. To better understand and analyse how this type of mistake arises, we focus on RDF-to-Text generation and explore two methods of probing…

The proliferation of retrieval-augmented generation (RAG) has established vector databases as critical infrastructure, yet they introduce severe privacy risks via embedding inversion attacks. Existing paradigms face a fundamental trade-off:…

With the rapid advancement of intelligent transportation systems, text-driven image generation and editing techniques have demonstrated significant potential in providing rich, controllable visual scene data for applications such as traffic…

Neural language models often fail to generate diverse and informative texts, limiting their applicability in real-world problems. While previous approaches have proposed to address these issues by identifying and penalizing undesirable…

Language models (LMs) have revolutionized the way we interact with information, but they often generate nonfactual text, raising concerns about their reliability. Previous methods use external knowledge as references for text generation to…

In this paper, we present an empirical study introducing a nuanced evaluation framework for text-to-image (T2I) generative models, applied to human image synthesis. Our framework categorizes evaluations into two distinct groups: first,…

Logical Natural Language Generation, i.e., generating textual descriptions that can be logically entailed by a structured table, has been a challenge due to the low fidelity of the generation. \citet{chen2020logic2text} have addressed this…

Despite the remarkable ability of large language models (LLMs) in language comprehension and generation, they often suffer from producing factually incorrect information, also known as hallucination. A promising solution to this issue is…

The Data-to-Text task aims to generate human-readable text for describing some given structured data enabling more interpretability. However, the typical generation task is confined to a few particular domains since it requires well-aligned…

Deepfake detection, the task of automatically discriminating machine-generated text, is increasingly critical with recent advances in natural language generative models. Existing approaches to deepfake detection typically represent…

The impressive ability of large language models to generate natural text across various tasks has led to critical challenges in authorship authentication. Although numerous detection methods have been developed to differentiate between…

Thanks to recent advancements in scalable deep architectures and large-scale pretraining, text-to-video generation has achieved unprecedented capabilities in producing high-fidelity, instruction-following content across a wide range of…

Knowledge-grounded dialogue systems are intended to convey information that is based on evidence provided in a given source text. We discuss the challenges of training a generative neural dialogue model for such systems that is controlled…

Recent advancements in Generative AI and Large Language Models (LLMs) have enabled the creation of highly realistic synthetic content, raising concerns about the potential for malicious use, such as misinformation and manipulation.…

Neural table-to-text generation models have achieved remarkable progress on an array of tasks. However, due to the data-hungry nature of neural models, their performances strongly rely on large-scale training examples, limiting their…

In ad text generation (ATG), desirable ad text is both faithful and informative. That is, it should be faithful to the input document, while at the same time containing important information that appeals to potential customers. The existing…

Retrieval-augmented generation systems often suffer from a gap between optimizing retrieval relevance and generative utility. With such a gap, retrieved documents may be topically relevant but still lack the content needed for effective…

Large Language Models (LLMs), when used for conditional text generation, often produce hallucinations, i.e., information that is unfaithful or not grounded in the input context. This issue arises in typical conditional text generation…

Deep-learning models for language generation tasks tend to produce repetitive output. Various methods have been proposed to encourage lexical diversity during decoding, but this often comes at a cost to the perceived fluency and adequacy of…

Data-to-text generation can be conceptually divided into two parts: ordering and structuring the information (planning), and generating fluent language describing the information (realization). Modern neural generation systems conflate…