Related papers: A Comparative Study of Controlled Text Generation …

While large language models (LLMs) have made significant strides in generating coherent and contextually relevant text, they often function as opaque black boxes, trained on vast unlabeled datasets with statistical objectives, lacking an…

Current end-to-end neural conversation models inherently lack the flexibility to impose semantic control in the response generation process, often resulting in uninteresting responses. Attempts to boost informativeness alone come at the…

While text-to-video diffusion models have advanced significantly, creating coherent long-form content remains unreliable due to stochastic sampling artifacts. This necessitates generating multiple candidates, yet verifying them creates a…

Talking Head Generation (THG) has emerged as a transformative technology in computer vision, enabling the synthesis of realistic human faces synchronized with image, audio, text, or video inputs. This paper provides a comprehensive review…

ETL (Extract, Transform, Load) tools such as IBM DataStage allow users to visually assemble complex data workflows, but configuring stages and their properties remains time consuming and requires deep tool knowledge. We propose a system…

Large language models (LLMs) have recently achieved notable success in code-generation benchmarks such as HumanEval and LiveCodeBench. However, a detailed examination reveals that these evaluation suites often comprise only a limited number…

The evaluation of generative models for natural image tasks has been extensively studied. Similar protocols and metrics are used in cases with unique particularities, such as Handwriting Generation, even if they might not be completely…

Paraphrase generation has been widely used in various downstream tasks. Most tasks benefit mainly from high quality paraphrases, namely those that are semantically similar to, yet linguistically diverse from, the original sentence.…

Procedural content generation via machine learning (PCGML) is typically framed as the task of fitting a generative model to full-scale examples of a desired content distribution. This approach presents a fundamental tension: the more design…

Large language models (LLMs) encode knowledge with varying degrees of confidence. When responding to queries, models face an inherent trade-off: they can generate responses that are less informative but highly factual, or more informative…

Natural language counterfactual generation aims to minimally modify a given text such that the modified text will be classified into a different class. The generated counterfactuals provide insight into the reasoning behind a model's…

Machine Learning has seen tremendous growth recently, which has led to larger adoption of ML systems for educational assessments, credit risk, healthcare, employment, criminal justice, to name a few. The trustworthiness of ML and NLP…

To meet the requirements of real-world applications, it is essential to control generations of large language models (LLMs). Prior research has tried to introduce reinforcement learning (RL) into controllable text generation while most…

This paper presents an innovative approach to enhance control over audio generation by emphasizing the alignment between audio and text representations during model training. In the context of language model-based audio generation, the…

Evaluating the quality of text generated by large language models (LLMs) remains a significant challenge. Traditional metrics often fail to align well with human judgments, particularly in tasks requiring creativity and nuance. In this…

Estimating the quality of register transfer level (RTL) designs is crucial in the electronic design automation (EDA) workflow, as it enables instant feedback on key metrics like area and delay without the need for time-consuming logic…

While recent advancements in the capabilities and widespread accessibility of generative language models, such as ChatGPT (OpenAI, 2022), have brought about various benefits by generating fluent human-like text, the task of distinguishing…

Large Language Models (LLMs) often struggle when prompted to generate content under specific constraints. However, in such cases it is often easy to check whether these constraints are satisfied or violated. Recent works have shown that…

We propose a Distributional Approach for addressing Controlled Text Generation from pre-trained Language Models (LMs). This approach permits to specify, in a single formal framework, both "pointwise" and "distributional" constraints over…

Game Description Generation (GDG) is the task of generating a game description written in a Game Description Language (GDL) from natural language text. Previous studies have explored generation methods leveraging the contextual…