Related papers: Self-Generative Adversarial Fine-Tuning for Large …
We introduce a lightweight yet highly effective safety guardrail framework for language models, demonstrating that small-scale language models can achieve, and even surpass, the performance of larger counterparts in content moderation…
Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms appended to harmful queries bypass safety alignment and trigger unintended…
Finding an agreement among diverse opinions is a challenging topic in multiagent systems. Recently, large language models (LLMs) have shown great potential in addressing this challenge due to their remarkable capabilities in comprehending…
Despite their remarkable reasoning capabilities across diverse domains, large language models (LLMs) face fundamental challenges in natively functioning as generative reasoning recommendation models (GRRMs), where the intrinsic modeling gap…
Large Language Models (LLMs), despite extensive pretraining on broad internet corpora, often struggle to adapt effectively to specialized domains. There is growing interest in fine-tuning these models for such domains; however, progress is…
With the rapid development of natural language processing technology, large-scale language models (LLM) have achieved remarkable results in a variety of tasks. However, how to effectively train these huge models and improve their…
With the wide application of large language models (LLMs), the problems of bias and value inconsistency in sensitive domains have gradually emerged, especially in terms of race, society and politics. In this paper, we propose an adversarial…
Recent advancements in large language models (LLMs) on language modeling and emergent capabilities make them a promising reference-free evaluator of natural language generation quality, and a competent alternative to human evaluation.…
Can large language models improve without external data -- by generating their own questions and answers? We hypothesize that a pre-trained language model can improve its reasoning skills given only a single prompt specifying the topic…
Open-source Large Language Models (LLMs) often employ safety alignment methods to resist harmful instructions. However, recent research shows that maliciously fine-tuning these LLMs on harmful data can easily bypass these safeguards. To…
As powerful Large Language Models (LLMs) are now widely used for numerous practical applications, their safety is of critical importance. While alignment techniques have significantly improved overall safety, LLMs remain vulnerable to…
Game Description Language (GDL) provides a standardized way to express diverse games in a machine-readable format, enabling automated game simulation, and evaluation. While previous research has explored game description generation using…
The prevailing approach to aligning Large Language Models (LLMs) typically relies on human or AI feedback and assumes access to specific types of preference datasets. In our work, we question the efficacy of such datasets and explore…
Generative adversarial networks (GANs) have great successes on synthesizing data. However, the existing GANs restrict the discriminator to be a binary classifier, and thus limit their learning capacity for tasks that need to synthesize…
Recent developments in Large Language Models (LLMs) have manifested significant advancements. To facilitate safeguards against malicious exploitation, a body of research has concentrated on aligning LLMs with human preferences and…
Background: Over the past few decades, the process and methodology of automated question generation (AQG) have undergone significant transformations. Recent progress in generative natural language models has opened up new potential in the…
Aligning large language models (LLMs) with human objectives is crucial for real-world applications. However, fine-tuning LLMs for alignment often suffers from unstable training and requires substantial computing resources. Test-time…
Large Language Models (LLMs) excel at various natural language processing tasks but remain vulnerable to jailbreaking attacks that induce harmful content generation. In this paper, we reveal a critical safety inconsistency: LLMs can more…
The alignment of large language models (LLMs) is crucial not only for unlocking their potential in specific tasks but also for ensuring that responses meet human expectations and adhere to safety and ethical principles. Current alignment…
While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks. However, traditional adversarial attacks are typically limited to single,…