Related papers: LAD: Language Models as Data for Zero-Shot Dialog

Existing dialog system models require extensive human annotations and are difficult to generalize to different tasks. The recent success of large pre-trained language models such as BERT and GPT-2 (Devlin et al., 2019; Radford et al., 2019)…

Zero-Shot Learning (ZSL) has attracted huge research attention over the past few years; it aims to learn the new concepts that have never been seen before. In classical ZSL algorithms, attributes are introduced as the intermediate semantic…

This paper introduces Unified Language-driven Zero-shot Domain Adaptation (ULDA), a novel task setting that enables a single model to adapt to diverse target domains without explicit domain-ID knowledge. We identify the constraints in the…

Large language models (LLMs) are powerful dialogue agents, but specializing them towards fulfilling a specific function can be challenging. Instructing tuning, i.e. tuning models on instruction and sample responses generated by humans…

The emerging zero-shot capabilities of Large Language Models (LLMs) have led to their applications in areas extending well beyond natural language processing tasks. In reinforcement learning, while LLMs have been extensively used in…

Current reinforcement learning objectives for large-model reasoning primarily focus on maximizing expected rewards. This paradigm can lead to overfitting to dominant reward signals, while neglecting alternative yet valid reasoning…

Significant progress has been made in vision-language models. However, language-conditioned robotic manipulation for contact-rich tasks remains underexplored, particularly in terms of tactile sensing. To address this gap, we introduce the…

Large pre-trained language models have brought remarkable progress in NLP. Pre-training and Fine-tuning have given state-of-art performance across tasks in text processing. Data Augmentation techniques have also helped build state-of-art…

Deep Neural Networks (DNNs) are known to be susceptible to adversarial attacks. Previous researches mainly focus on improving adversarial robustness in the fully supervised setting, leaving the challenging domain of zero-shot adversarial…

The recent advent of large language models has reinvigorated debate over whether human cognitive capacities might emerge in such generic models given sufficient training data. Of particular interest is the ability of these models to reason…

Task-oriented dialog systems enable users to accomplish tasks using natural language. State-of-the-art systems respond to users in the same way regardless of their personalities, although personalizing dialogues can lead to higher levels of…

Recent work has investigated the capabilities of large language models (LLMs) as zero-shot models for generating individual-level characteristics (e.g., to serve as risk models or augment survey datasets). However, when should a user have…

Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task. While typically task-agnostic in architecture, this method still requires…

Recently, Large Language Models (LLMs) have emerged as an alternative to training task-specific dialog agents, due to their broad reasoning capabilities and performance in zero-shot learning scenarios. However, many LLM-based dialog systems…

By encoding time series as a string of numerical digits, we can frame time series forecasting as next-token prediction in text. Developing this approach, we find that large language models (LLMs) such as GPT-3 and LLaMA-2 can surprisingly…

Task-oriented dialogue (TOD) system is designed to accomplish user-defined tasks through dialogues. The TOD system has progressed towards end-to-end modeling by leveraging pre-trained large language models. Fine-tuning the pre-trained…

Pretrained language models (PLMs) have demonstrated remarkable performance in various natural language processing tasks: Unidirectional PLMs (e.g., GPT) are well known for their superior text generation capabilities; bidirectional PLMs…

In spite of the rapid advancements in unsupervised log anomaly detection techniques, the current mainstream models still necessitate specific training for individual system datasets, resulting in costly procedures and limited scalability…

Despite the promising results of current cross-lingual models for spoken language understanding systems, they still suffer from imperfect cross-lingual representation alignments between the source and target languages, which makes the…

Recently, utilizing deep neural networks to build the opendomain dialogue models has become a hot topic. However, the responses generated by these models suffer from many problems such as responses not being contextualized and tend to…