Related papers: Logic-Consistency Text Generation from Semantic Pa…

Consistency, which refers to the capability of generating the same predictions for semantically similar contexts, is a highly desirable property for a sound language understanding model. Although recent pretrained language models (PLMs)…

Existing text-to-SQL synthesis pipelines still conflate executability with semantic validity: syntactic checks and execution-based validation can retain queries that execute successfully while violating database semantics. To address these…

Nearly all general-purpose neural semantic parsers generate logical forms in a strictly top-down autoregressive fashion. Though such systems have achieved impressive results across a variety of datasets and domains, recent works have called…

Large Language Models have significantly advanced natural language processing tasks, but remain prone to generating incorrect or misleading but plausible arguments. This issue, known as hallucination, is particularly concerning in…

Many computer systems are now being redesigned to incorporate LLM-powered agents, enabling natural language input and more flexible operations. This paper focuses on handling database transactions created by large language models (LLMs).…

Grammar Error Correction(GEC) mainly relies on the availability of high quality of large amount of synthetic parallel data of grammatically correct and erroneous sentence pairs. The quality of the synthetic data is evaluated on how well the…

Text-to-image generation has been increasingly applied in medical domains for various purposes such as data augmentation and education. Evaluating the quality and clinical reliability of these generated images is essential. However,…

Lexical Semantic Change (LSC) provides insight into cultural and social dynamics. Yet, the validity of methods for measuring different kinds of LSC remains unestablished due to the absence of historical benchmark datasets. To address this…

Co-speech gesture generation enhances human-computer interaction realism through speech-synchronized gesture synthesis. However, generating semantically meaningful gestures remains a challenging problem. We propose SARGes, a novel framework…

Accurate sentiment analysis of texts is crucial for a variety of applications, such as understanding customer feedback, monitoring market trends, and detecting public sentiment. However, manually annotating large sentiment corpora for…

Semantic Parsing aims to capture the meaning of a sentence and convert it into a logical, structured form. Previous studies show that semantic parsing enhances the performance of smaller models (e.g., BERT) on downstream tasks. However, it…

While Large Language Models (LLMs) have demonstrated remarkable capabilities, their reliability is significantly compromised by hallucinations. Existing intrinsic self-correction methods attempt to address this, but often fail due to…

Sequential structure is a key feature of multiple domains of natural cognition and behavior, such as language, movement and decision-making. Likewise, it is also a central property of tasks to which we would like to apply artificial…

Achieving reliable communication has long been a fundamental challenge in networked systems. Semantic Error Correction (SEC) leverages the semantic understanding capabilities of language models (LMs) to perform application-layer error…

Eliciting reasoning capabilities from language models (LMs) is a critical direction on the path towards building intelligent systems. Most recent studies dedicated to reasoning focus on out-of-distribution performance on…

For building question answering systems and natural language interfaces, semantic parsing has emerged as an important and powerful paradigm. Semantic parsers map natural language into logical forms, the classic representation for many…

We study the ability of large language models (LLMs) to generate comprehensive and accurate book summaries solely from their internal knowledge, without recourse to the original text. Employing a diverse set of books and multiple LLM…

We present a comparison of word-based and character-based sequence-to-sequence models for data-to-text natural language generation, which generate natural language descriptions for structured inputs. On the datasets of two recent generation…

Self-training approach for large language models (LLMs) improves reasoning abilities by training the models on their self-generated rationales. Previous approaches have labeled rationales that produce correct answers for a given question as…

Recent studies show that pre-trained language models (LMs) are vulnerable to textual adversarial attacks. However, existing attack methods either suffer from low attack success rates or fail to search efficiently in the exponentially large…