相关论文: BRIDGE: Bootstrapping Text to Control Time-Series …
While GPT-2 generates sentences that are remarkably human-like, longer documents can ramble and do not follow human-like writing structure. We study the problem of imposing structure on long-range text. We propose a novel controlled text…
Natural language serves as a common and straightforward signal for humans to interact seamlessly with machines. Recognizing the importance of this interface, the machine learning community is investing considerable effort in generating data…
The Data-to-Text task aims to generate human-readable text for describing some given structured data enabling more interpretability. However, the typical generation task is confined to a few particular domains since it requires well-aligned…
In the field of educational assessment, automated scoring systems increasingly rely on deep learning and large language models (LLMs). However, these systems face significant risks of bias amplification, where model prediction gaps between…
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…
Constrained generative modeling is fundamental to applications such as robotic control and autonomous driving, where models must respect physical laws and safety-critical constraints. In real-world settings, these constraints rarely take…
Simultaneous generation models write generation results while reading streaming inputs, necessitating a policy-maker to determine the appropriate output timing. Existing simultaneous generation methods generally adopt the traditional…
Recent advancements in large language models (LLMs) have demonstrated remarkable text generation capabilities. However, controlling specific attributes of generated text remains challenging without architectural modifications or extensive…
Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation. An alternative solution is to rely on automatic text generation which,…
We introduce a novel, training-free approach for enhancing alignment in Transformer-based Text-Guided Diffusion Models (TGDMs). Existing TGDMs often struggle to generate semantically aligned images, particularly when dealing with complex…
Recent advances in text-to-speech (TTS) have enabled natural speech synthesis, but fine-grained, time-varying emotion control remains challenging. Existing methods often allow only utterance-level control and require full model fine-tuning…
We introduce MTG, a new benchmark suite for training and evaluating multilingual text generation. It is the first-proposed multilingual multiway text generation dataset with the largest human-annotated data (400k). It includes four…
As Large Language Models (LLMs) are deployed more widely, customization with respect to vocabulary, style, and character becomes more important. In this work, we introduce model arithmetic, a novel inference framework for composing and…
Controllable text generation concerns two fundamental tasks of wide applications, namely generating text of given attributes (i.e., attribute-conditional generation), and minimally editing existing text to possess desired attributes (i.e.,…
Generating large-scale sensing datasets through photo-realistic simulation is an important aspect of many robotics applications such as autonomous driving. In this paper, we consider the problem of synchronous data collection from the…
Large Language Models (LLMs) and Foundation Models (FMs) have recently become prevalent for time series forecasting tasks. While fine-tuning LLMs enables domain adaptation, they often struggle to generalize across diverse and unseen…
This study addresses the challenge that generative models struggle to balance flexibility, stability, and controllability in complex interactive scenarios. It proposes a controllable generation framework for dynamic interactive content…
Effective mental health counseling is a complex, theory-driven process requiring the simultaneous integration of psychological frameworks, real-time distress signals, and strategic intervention planning. This level of clinical reasoning is…
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…
In recent years, significant progress has been made in the development of text-to-image generation models. However, these models still face limitations when it comes to achieving full controllability during the generation process. Often,…