Related papers: CoCon: A Self-Supervised Approach for Controlled T…
Controlling the attribute intensity of text generation is crucial across scenarios (e.g., writing conciseness, chatting emotion, and explanation clarity). The remarkable capabilities of large language models (LLMs) have revolutionized text…
Although significant progress has been made in many tasks within the field of Natural Language Processing (NLP), Controlled Text Generation (CTG) continues to face numerous challenges, particularly in achieving fine-grained conditional…
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…
Recent years have witnessed a rapid growth of large-scale language models in the domain of music audio. Such models enable end-to-end generation of higher-quality music, and some allow conditioned generation using text descriptions.…
Recent diffusion models achieve strong photorealism and fluency in video generation, yet remain fragile under abstract, sparse or complex conditions, leading to poor performance in professional production workflows such as storyboard…
The remarkable performance of large language models (LLMs) in zero-shot language understanding has garnered significant attention. However, employing LLMs for large-scale inference or domain-specific fine-tuning requires immense…
Conditional text generation often requires lexical constraints, i.e., which words should or shouldn't be included in the output text. While the dominant recipe for conditional text generation has been large-scale pretrained language models…
Large language models (LLMs) have achieved notable success in code generation. However, they still frequently produce uncompilable output because their next-token inference procedure does not model formal aspects of code. Although…
Representation learning for text via pretraining a language model on a large corpus has become a standard starting point for building NLP systems. This approach stands in contrast to autoencoders, also trained on raw text, but with the…
Generating coherent and cohesive long-form texts is a challenging task. Previous works relied on large amounts of human-generated texts to train neural language models. However, few attempted to explicitly improve neural language models…
The paper describes a system that uses large language model (LLM) technology to support the automatic learning of new entries in an intelligent agent's semantic lexicon. The process is bootstrapped by an existing non-toy lexicon and a…
We present a self-supervised learning framework, COCO-LM, that pretrains Language Models by COrrecting and COntrasting corrupted text sequences. Following ELECTRA-style pretraining, COCO-LM employs an auxiliary language model to corrupt…
Conditional natural language generation methods often require either expensive fine-tuning or training a large language model from scratch. Both are unlikely to lead to good results without a substantial amount of data and computational…
A wide range of control perspectives have been explored in controllable text generation. Structure-controlled summarization is recently proposed as a useful and interesting research direction. However, current structure-controlling methods…
The robustness of AI-content detection models against sophisticated adversarial strategies, such as paraphrasing or word switching, is a rising concern in natural language generation (NLG) applications. This study proposes ToBlend, a novel…
A wide range of LM applications require generating text that conforms to syntactic or semantic constraints. Imposing such constraints can be naturally framed as probabilistic conditioning, but exact generation from the resulting…
Self-correction has demonstrated potential in code generation by allowing language models to revise and improve their outputs through successive refinement. Recent studies have explored prompting-based strategies that incorporate…
We propose a novel framework for controllable natural language transformation. Realizing that the requirement of parallel corpus is practically unsustainable for controllable generation tasks, an unsupervised training scheme is introduced.…
Unsupervised text attribute transfer automatically transforms a text to alter a specific attribute (e.g. sentiment) without using any parallel data, while simultaneously preserving its attribute-independent content. The dominant approaches…
Like humans, Large Language Models (LLMs) struggle to generate high-quality long-form text that adheres to strict requirements in a single pass. This challenge is unsurprising, as successful human writing, according to the Cognitive Writing…