Related papers: Hierarchical Latent Structures in Data Generation …

Translation into morphologically-rich languages challenges neural machine translation (NMT) models with extremely sparse vocabularies where atomic treatment of surface forms is unrealistic. This problem is typically addressed by either…

Human languages have evolved to be structured through repeated language learning and use. These processes introduce biases that operate during language acquisition and shape linguistic systems toward communicative efficiency. In this paper,…

The Neural Contextual Reinforcement Framework introduces an innovative approach to enhancing the logical coherence and structural consistency of text generated by large language models. Leveraging reinforcement learning principles, the…

While Large Language Models (LLMs) demonstrate remarkable proficiency in semantic understanding, they often struggle to ensure structural consistency and reasoning reliability in complex decision-making tasks that demand rigorous logic.…

Conversational systems should generate diverse language forms to interact fluently and accurately with users. In this context, Natural Language Generation (NLG) engines convert Meaning Representations (MRs) into sentences, directly…

Inductive reasoning is a core problem-solving capacity: humans can identify underlying principles from a few examples, which robustly generalize to novel scenarios. Recent work evaluates large language models (LLMs) on inductive reasoning…

Learning hierarchical structures in sequential data -- from simple algorithmic patterns to natural language -- in a reliable, generalizable way remains a challenging problem for neural language models. Past work has shown that recurrent…

Prompt learning has become a prevalent strategy for adapting vision-language foundation models (VLMs) such as CLIP to downstream tasks. With the emergence of large language models (LLMs), recent studies have explored the potential of using…

Syntactic structures used to play a vital role in natural language processing (NLP), but since the deep learning revolution, NLP has been gradually dominated by neural models that do not consider syntactic structures in their design. One…

Metaphors are common in everyday language, and the identification and understanding of metaphors are facilitated by models to achieve a better understanding of the text. Metaphors are mainly identified and generated by pre-trained models in…

We introduce Transformer Grammars (TGs), a novel class of Transformer language models that combine (i) the expressive power, scalability, and strong performance of Transformers and (ii) recursive syntactic compositions, which here are…

Modern generative machine learning models demonstrate surprising ability to create realistic outputs far beyond their training data, such as photorealistic artwork, accurate protein structures, or conversational text. These successes…

Transformer models exhibit in-context learning: the ability to accurately predict the response to a novel query based on illustrative examples in the input sequence. In-context learning contrasts with traditional in-weights learning of…

The generation of high-fidelity synthetic data is a cornerstone of modern machine learning, yet Large Language Models (LLMs) frequently suffer from hallucinations, logical inconsistencies, and mode collapse when tasked with structured…

Large language models (LLMs) are increasingly used as substitutes for human subjects in behavioral simulations, including synthetic social network generation. Yet it remains unclear how their relational outputs depend on prompt design,…

This article analyzes the use of Large Language Models (LLMs) as support for the conceptual modeling of relational databases through the automatic generation of Entity-Relationship (ER) diagrams from natural language requirements. The…

Large language models (LLMs) have shown promising results in a wide array of generative NLP tasks, such as summarization and machine translation. In the context of narrative generation, however, existing models still do not capture factors…

Pretrained masked language models (MLMs) have demonstrated an impressive capability to comprehend and encode conceptual knowledge, revealing a lattice structure among concepts. This raises a critical question: how does this…

Hypothetical induction is recognized as the main reasoning type when scientists make observations about the world and try to propose hypotheses to explain those observations. Past research on hypothetical induction is under a constrained…

We present HILGEN, a Hierarchically-Informed Data Generation approach that combines domain knowledge from the Unified Medical Language System (UMLS) with synthetic data generated by large language models (LLMs), specifically GPT-3.5. Our…