12 papers
Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods
Yulin Chen, Haoran Li, Yuan Sui +2
With the development of technology, large language models (LLMs) have dominated the downstream natural language processing (NLP) tasks. However, because of the LLMs' instruction-fo…
What-If Analysis of Large Language Models: Explore the Game World Using Proactive Thinking
Yuan Sui, Yanming Zhang, Yi Liao +5
LLMs struggle with decision-making in high-stakes environments like MOBA games, primarily due to a lack of proactive reasoning and limited understanding of complex game dynamics. T…
Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance
Yufei He, Ruoyu Li, Alex Chen +8
Large language model (LLM) agents often struggle in environments where rules and required domain knowledge frequently change, such as regulatory compliance and user risk screening.…
TopicAttack: An Indirect Prompt Injection Attack via Topic Transition
Yulin Chen, Haoran Li, Yuexin Li +3
Large language models (LLMs) have shown remarkable performance across a range of NLP tasks. However, their strong instruction-following capabilities and inability to distinguish in…
Efficient Reasoning via Chain of Unconscious Thought
Ruihan Gong, Yue Liu, Wenjie Qu +11
Large Reasoning Models (LRMs) achieve promising performance but compromise token efficiency due to verbose reasoning processes. Unconscious Thought Theory (UTT) posits that complex…
Safety in Large Reasoning Models: A Survey
Cheng Wang, Yue Liu, Baolong Bi +9
Large Reasoning Models (LRMs) have exhibited extraordinary prowess in tasks like mathematics and coding, leveraging their advanced reasoning capabilities. Nevertheless, as these ca…