Related papers: Self-Generative Adversarial Fine-Tuning for Large …

Reinforcement learning (RL) has become a central post-training paradigm for large language models (LLMs), but its performance is highly sensitive to the quality of training problems. This sensitivity stems from the non-stationarity of RL:…

Large language models (LLMs) often struggle with knowledge intensive NLP tasks, such as answering "Who won the latest World Cup?" because the knowledge they learn during training may be insufficient or outdated. Conditioning generation on…

Language is a ubiquitous tool that is foundational to reasoning and collaboration, ranging from everyday interactions to sophisticated problem-solving tasks. The establishment of a common language can serve as a powerful asset in ensuring…

Retrieval-augmented generation (RAG) enhances the question-answering (QA) abilities of large language models (LLMs) by integrating external knowledge. However, adapting general-purpose RAG systems to specialized fields such as science and…

Recent advances show that large language models (LLMs) generalize strong performance across different natural language benchmarks. However, the large size of LLMs makes training and inference expensive and impractical to run in…

Pre-trained language models (PLMs) have been widely used to underpin various downstream tasks. However, the adversarial attack task has found that PLMs are vulnerable to small perturbations. Mainstream methods adopt a detached two-stage…

Generative Adversarial Networks (GANs) have achieved remarkable results in the task of generating realistic natural images. In most successful applications, GAN models share two common aspects: solving a challenging saddle point…

Melody generation from lyrics has been a challenging research issue in the field of artificial intelligence and music, which enables to learn and discover latent relationship between interesting lyrics and accompanying melody.…

When performing tasks like automatic speech recognition or spoken language understanding for a given utterance, access to preceding text or audio provides contextual information can improve performance. Considering the recent advances in…

In the rapidly evolving field of machine learning, adversarial attacks present a significant challenge to model robustness and security. Decision-based attacks, which only require feedback on the decision of a model rather than detailed…

Large Language Models (LLMs) excel at code generation, yet their outputs often contain subtle bugs, for which effective test cases are a critical bottleneck. Existing test generation methods, whether based on prompting or supervised…

Large Language Model (LLM) based agents are powerful yet fundamentally static after deployment, lacking the ability to autonomously expand capabilities, generate new tools, or evolve their reasoning. This work introduces a hierarchical…

Generative adversarial networks (GANs) have achieved remarkable progress in recent years, but the continuously growing scale of models makes them challenging to deploy widely in practical applications. In particular, for real-time…

Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations. Current approaches focus on using reinforcement learning with human…

We propose a novel approach for training large language models (LLMs) to adhere to objectives defined within a latent embedding space. Our method leverages reinforcement learning (RL), treating a pre-trained LLM as an environment. Our…

Large language model alignment is widely used and studied to avoid LLM producing unhelpful and harmful responses. However, the lengthy training process and predefined preference bias hinder adaptation to online diverse human preferences. To…

We study self-rewarding reasoning large language models (LLMs), which can simultaneously generate step-by-step reasoning and evaluate the correctness of their outputs during the inference time-without external feedback. This integrated…

Supervised fine-tuning (SFT) and alignment of large language models (LLMs) are key steps in providing a good user experience. However, the concept of an appropriate alignment is inherently application-dependent, and current methods often…

Deep generative models can learn to generate realistic-looking images, but many of the most effective methods are adversarial and involve a saddlepoint optimization, which requires a careful balancing of training between a generator network…

While deep learning in the form of recurrent neural networks (RNNs) has caused a significant improvement in neural language modeling, the fact that they are extremely prone to overfitting is still a mainly unresolved issue. In this paper we…