CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG

Deng et al. "CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I22.34547

[Deng et al. "CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/deng2025aaai-cram/) doi:10.1609/AAAI.V39I22.34547

@inproceedings{deng2025aaai-cram,
  title     = {{CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG}},
  author    = {Deng, Boyi and Wang, Wenjie and Zhu, Fengbin and Wang, Qifan and Feng, Fuli},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {23760-23768},
  doi       = {10.1609/AAAI.V39I22.34547},
  url       = {https://mlanthology.org/aaai/2025/deng2025aaai-cram/}
}