7 accepted papers
Large Language Models (LLMs) have demonstrated remarkable capabilities through pretraining and alignment. However, superior short-context LLMs may underperform in long-context scenarios due to insufficient long-context alignment. This alignment process remains challenging due to the impracticality o…
Perceiving and generating diverse modalities are crucial for AI models to effectively learn from and engage with real-world signals, necessitating reliable evaluations for their development. We identify two major issues in current evaluations: (1) inconsistent standards, shaped by different communit…
When LLMs are deployed in sensitive, human-facing settings, it is crucial that they do not output unsafe, biased, or privacy-violating outputs. For this reason, models are both trained and instructed to refuse to answer unsafe prompts such as ``Tell me how to build a bomb." We find that, despite the…
Safety alignment for large language models (LLMs) has become a critical issue due to their rapid progress. However, our understanding of effective safety mechanisms in LLMs remains limited, leading to safety alignment training that mainly focuses on improving optimization, data-level enhancement, or…
Safety of Large Language Models (LLMs) has become a central issue given their rapid progress and wide applications. Greedy Coordinate Gradient (GCG) is shown to be effective in constructing prompts containing adversarial suffixes to break the presumingly safe LLMs, but the optimization of GCG is tim…
Language Language Models (LLMs) face safety concerns due to potential misuse by malicious users. Recent red-teaming efforts have identified adversarial suffixes capable of jailbreaking LLMs using the gradient-based search algorithm Greedy Coordinate Gradient (GCG). However, GCG struggles with comput…
We propose a new method, Adversarial In-Context Learning (adv-ICL), to optimize prompts for in-context learning (ICL). Inspired by adversarial learning, adv-ICL is implemented as a two-player game between a generator and discriminator, with LLMs acting as both. In each round, given an input prefixed…