Related papers: On Characterizations for Language Generation: Inte…

Neural text generation is a key tool in natural language applications, but it is well known there are major problems at its core. In particular, standard likelihood training and decoding leads to dull and repetitive outputs. While some…

The emergence of large language models (LLMs) has significantly advanced the development of natural language processing (NLP), especially in text generation tasks like question answering. However, model hallucinations remain a major…

Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to process long contexts, yet a notable gap remains in generating long, aligned outputs. This limitation stems from a training gap where…

Benchmarks measure whether a model is correct. They do not measure whether a model is reliable. This distinction is largely academic for single-shot inference, but becomes critical for agentic AI systems, where a single rephrased prompt can…

This paper demonstrates the robustness of Lipschitz-regularized $\alpha$-divergences as objective functionals in generative modeling, showing they enable stable learning across a wide range of target distributions with minimal assumptions.…

The Large Visual Language Models (LVLMs) enhances user interaction and enriches user experience by integrating visual modality on the basis of the Large Language Models (LLMs). It has demonstrated their powerful information processing and…

Recurrent neural networks empirically generate natural language with high syntactic fidelity. However, their success is not well-understood theoretically. We provide theoretical insight into this success, proving in a finite-precision…

Natural Language Generation (NLG), and more generally generative AI, are among the currently most impactful research fields. Creative NLG, such as automatic poetry generation, is a fascinating niche in this area. While most previous…

Hallucination of text ungrounded in the input is a well-known problem in neural data-to-text generation. Many methods have been proposed to mitigate it, but they typically require altering model architecture or collecting additional data,…

Code generation aims to automatically generate code from input requirements, significantly enhancing development efficiency. Recent large language models (LLMs) based approaches have shown promising results and revolutionized code…

The use of language models for generating lyrics and poetry has received an increased interest in the last few years. They pose a unique challenge relative to standard natural language problems, as their ultimate purpose is reative, notions…

To ensure large language models (LLMs) are used safely, one must reduce their propensity to hallucinate or to generate unacceptable answers. A simple and often used strategy is to first let the LLM generate multiple hypotheses and then…

Many recent works have discussed the propensity, or lack thereof, for emergent languages to exhibit properties of natural languages. A favorite in the literature is learning compositionality. We note that most of those works have focused on…

Many language generation tasks require the production of text conditioned on both structured and unstructured inputs. We present a novel neural network architecture which generates an output sequence conditioned on an arbitrary number of…

Hallucinations in large language models (LLMs) are always seen as limitations. However, could they also be a source of creativity? This survey explores this possibility, suggesting that hallucinations may contribute to LLM application by…

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…

With recent advances in large language models (LLMs), the concept of automatically generating children's educational materials has become increasingly realistic. Working toward the goal of age-appropriate simplicity in generated educational…

Video generation has achieved remarkable progress, with generated videos increasingly resembling real ones. However, the rapid advance in generation has outpaced the development of adequate evaluation metrics. Currently, the assessment of…

Detecting hallucinations in large language model (LLM) outputs is pivotal, yet traditional fine-tuning for this classification task is impeded by the expensive and quickly outdated annotation process, especially across numerous vertical…

Trustworthiness of generative language models (GLMs) is crucial in their deployment to critical decision making systems. Hence, certified risk control methods such as selective prediction and conformal prediction have been applied to…