9 papers · 1 filter
Self-Exploring Language Models for Explainable Link Forecasting on Temporal Graphs via Reinforcement Learning
Zifeng Ding, Shenyang Huang, Zeyu Cao +11
Forecasting future links is a central task in temporal graph (TG) reasoning, requiring models to leverage historical interactions to predict upcoming ones. Traditional neural appro…
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…
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.…
VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents
Tri Cao, Bennett Lim, Yue Liu +7
Computer-Use Agents (CUAs) with full system access enable powerful task automation but pose significant security and privacy risks due to their ability to manipulate files, access…
Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction
Yulin Chen, Haoran Li, Yuan Sui +8
Large language models (LLMs) have demonstrated impressive performance and have come to dominate the field of natural language processing (NLP) across various tasks. However, due to…
Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?
Yufei He, Yuexin Li, Jiaying Wu +3
As large language models (LLMs) continue to evolve, ensuring their alignment with human goals and values remains a pressing challenge. A key concern is \textit{instrumental converg…
Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models
Yuan Sui, Yufei He, Tri Cao +3
Large Language Models (LLMs) often struggle with computational efficiency and error propagation in multi-step reasoning tasks. While recent advancements on prompting and post-train…
Can Indirect Prompt Injection Attacks Be Detected and Removed?
Yulin Chen, Haoran Li, Yuan Sui +4
Prompt injection attacks manipulate large language models (LLMs) by misleading them to deviate from the original input instructions and execute maliciously injected instructions, b…
UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphs
Yufei He, Yuan Sui, Xiaoxin He +3
Existing foundation models, such as CLIP, aim to learn a unified embedding space for multimodal data, enabling a wide range of downstream web-based applications like search, recomm…