相关论文: LiFi: Lightweight Controlled Text Generation with …

As the text generation capabilities of large language models become increasingly prominent, recent studies have focused on controlling particular aspects of the generated text to make it more personalized. However, most research on…

This paper proposes a simple method for controllable text generation based on weighting logits with a free-form classifier, namely CAIF sampling. Using an arbitrary text classifier, we adjust a small part of a language model's logits and…

Controlled text generation is a very important task in the arena of natural language processing due to its promising applications. In order to achieve this task we mainly introduce the novel soft prompt tuning method of using soft prompts…

Steering language generation towards objectives or away from undesired content has been a long-standing goal in utilizing language models (LM). Recent work has demonstrated reinforcement learning and weighted decoding as effective…

The recent large-scale generative modeling has attained unprecedented performance especially in producing high-fidelity images driven by text prompts. Text inversion (TI), alongside the text-to-image model backbones, is proposed as an…

Prefix-tuning is a powerful lightweight technique for adapting a large pre-trained language model to a downstream application. However, it uses the same dataset-level tuned prompt for all examples in the dataset. We extend this idea and…

Text-to-image generative models have made significant advancements in recent years; however, accurately capturing intricate details in textual prompts-such as entity missing, attribute binding errors, and incorrect relationships remains a…

Controllable text generation is a fundamental aspect of natural language generation, with numerous methods proposed for different constraint types. However, these approaches often require significant architectural or decoding modifications,…

Recently, there has been an increasing interest in developing diffusion-based text-to-image generative models capable of generating coherent and well-formed visual text. In this paper, we propose a novel and efficient approach called…

Fine-tuning pre-trained language models (LMs) is essential for enhancing their capabilities. Existing techniques commonly fine-tune on input-output pairs (e.g., instruction tuning) or with numerical rewards that gauge the output quality…

Recent advances in large pre-trained language models have demonstrated strong results in generating natural languages and significantly improved performances for many natural language generation (NLG) applications such as machine…

Controllable text generation systems often leverage control codes to direct various properties of the output like style and length. Inspired by recent work on causal inference for NLP, this paper reveals a previously overlooked flaw in…

Large language models benefit from training with a large amount of unlabeled text, which gives them increasingly fluent and diverse generation capabilities. However, using these models for text generation that takes into account target…

Recent works have sought to enhance the controllability and precision of text-driven motion generation. Some approaches leverage large language models (LLMs) to produce more detailed texts, while others incorporate global 3D coordinate…

While most research on controllable text generation has focused on steering base Language Models, the emerging instruction-tuning and prompting paradigm offers an alternate approach to controllability. We compile and release ConGenBench, a…

Text generation often requires high-precision output that obeys task-specific rules. This fine-grained control is difficult to enforce with off-the-shelf deep learning models. In this work, we consider augmenting neural generation models…

Automatically generating symbolic music-music scores tailored to specific human needs-can be highly beneficial for musicians and enthusiasts. Recent studies have shown promising results using extensive datasets and advanced transformer…

The growing collaboration between humans and AI models in generative tasks has introduced new challenges in distinguishing between human-written, LLM-generated, and human-LLM collaborative texts. In this work, we collect a multilingual,…

Current text-to-image diffusion models excel at generating diverse, high-quality images, yet they struggle to incorporate fine-grained camera metadata such as precise aperture settings. In this work, we introduce a novel text-to-image…

Large language models generate fluent texts and can follow natural language instructions to solve a wide range of tasks without task-specific training. Nevertheless, it is notoriously difficult to control their generation to satisfy the…