Papers with open-ended applications
Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection (2024.naacl-long)
Copied to clipboard
Jun Yan, Vikas Yadav, Shiyang Li, Lichang Chen, Zheng Tang, Hai Wang, Vijay Srinivasan, Xiang Ren, Hongxia Jin
| Challenge: | Instruction-tuned Large Language Models (LLMs) can modulate responses based on human instructions, but they can be maliciously steered to impact society in subtle but persistent ways. |
| Approach: | They propose a backdoor attack setting that allows an attacker to inject a virtual prompt into an LLM to steer it without any explicit injection at its input. |
| Outcome: | The proposed method is able to poison the model's instruction tuning data and show that it is highly effective in steering the model. |
Odysseus Navigates the Sirens’ Song: Dynamic Focus Decoding for Factual and Diverse Open-Ended Text Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing decoding methods struggle to balance factuality and diversity . Deterministic decoding approaches suffer from degeneration and lack of diversity - a problem that is not addressed by the current literature. |
| Approach: | They propose a plug-and-play stochastic approach that adjusts decoding focus based on distributional differences across layers, leveraging the modular nature of factual knowledge within LLMs. |
| Outcome: | Extensive experiments on seven datasets show that DFD significantly improves performance. |