Related papers: Controllable Text Generation with Residual Memory …
In this paper, we propose a novel controllable text-to-image generative adversarial network (ControlGAN), which can effectively synthesise high-quality images and also control parts of the image generation according to natural language…
There is enormous enthusiasm and concerns in using large language models (LLMs) in healthcare, yet current assumptions are all based on general-purpose LLMs such as ChatGPT. This study develops a clinical generative LLM, GatorTronGPT, using…
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…
The residual stream acts as a memory bus where transformer layers both store and access features (Elhage et al., 2021). We consider changing the mechanism for retrieving and storing information in the residual stream, and replace the…
Previous work on controllable text generation has explored the idea of control from the latent space, such as optimizing a representation with attribute-related classifiers or sampling a representation from relevant discrete samples.…
Recent breakthroughs in Large Language Models (LLMs), such as GPT-3 and Codex, now enable software developers to generate code based on a natural language prompt. Within computer science education, researchers are exploring the potential…
Large language models (LM) based on Transformers allow to generate plausible long texts. In this paper, we explore how this generation can be further controlled at decoding time to satisfy certain constraints (e.g. being non-toxic,…
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…
The deployment of large language models (LLMs) like ChatGPT and Gemini has shown their powerful natural language generation capabilities. However, these models can inadvertently learn and retain sensitive information and harmful content…
The automatic generation of RTL code (e.g., Verilog) using natural language instructions and large language models (LLMs) has attracted significant research interest recently. However, most existing approaches heavily rely on commercial…
With the rapid development of large language models (LLMs), the applications of LLMs have grown substantially. In the education domain, LLMs demonstrate significant potential, particularly in automatic text generation, which enables the…
Large Transformer-based language models can aid human authors by suggesting plausible continuations of text written so far. However, current interactive writing assistants do not allow authors to guide text generation in desired topical…
Large-scale transformer-based language models (LMs) demonstrate impressive capabilities in open text generation. However, controlling the generated text's properties such as the topic, style, and sentiment is challenging and often requires…
Large Language Models (LLMs) have emerged as influential instruments within the realm of natural language processing; nevertheless, their capacity to handle multi-party conversations (MPCs) -- a scenario marked by the presence of multiple…
In recent years, generative AI has undergone major advancements, demonstrating significant promise in augmenting human productivity. Notably, large language models (LLM), with ChatGPT-4 as an example, have drawn considerable attention.…
The rapid advancement of large language models (LLMs) such as GPT-3, PaLM, and Llama has significantly transformed natural language processing, showcasing remarkable capabilities in understanding and generating language. However, a…
Despite significant advancements in natural language generation, controlling language models to produce texts with desired attributes remains a formidable challenge. In this work, we introduce RSA-Control, a training-free controllable text…
Recent advancements in large language models (LLMs) have led to significant progress in text-based dialogue systems. These systems can now generate high-quality responses that are accurate and coherent across a wide range of topics and…
Recent developments in neural networks have led to the advance in data-to-text generation. However, the lack of ability of neural models to control the structure of generated output can be limiting in certain real-world applications. In…
Large Language Models (LLMs) present massive inherent knowledge and superior semantic comprehension capability, which have revolutionized various tasks in natural language processing. Despite their success, a critical gap remains in…