| language: | |
| - en | |
| license: apache-2.0 | |
| pipeline_tag: text-generation | |
| library_name: transformers | |
| # SHIFT: Gate-Modulated Activation Steering for Knowledge Conflict Mitigation in Retrieval-Augmented Generation | |
| This repository contains the model checkpoints for **SHIFT**, a lightweight framework designed to resolve knowledge conflicts in retrieval-augmented generation (RAG). | |
| - **Paper:** [SHIFT: Gate-Modulated Activation Steering for Knowledge Conflict Mitigation in Retrieval-Augmented Generation](https://huggingface.co/papers/2606.27786) | |
| - **Repository:** [GitHub - OpenBMB/SHIFT](https://github.com/OpenBMB/SHIFT) | |
| ## Method Overview | |
| SHIFT reformulates neuron-level modification as a learnable gate modulation, allowing LLMs to adaptively regulate internal activations for knowledge conflict resolution. Technically, SHIFT equips LLMs with a lightweight gate module and optimizes fewer than 0.01% trainable parameters while keeping the backbone model frozen. During generation, the gate module adjusts the model's internal representations to adaptively leverage contextual and parametric knowledge. | |
| ## Setup and Usage | |
| Please refer to the official [GitHub Repository](https://github.com/OpenBMB/SHIFT) for detailed environment setup, training, and evaluation scripts. | |
| ## Citation | |
| If you find this work useful, please cite the paper: | |
| ```bibtex | |
| @misc{li2026shiftgatemodulatedactivationsteering, | |
| title={SHIFT: Gate-Modulated Activation Steering for Knowledge Conflict Mitigation in Retrieval-Augmented Generation}, | |
| author={Ruochang Li and Pengcheng Huang and Zhenghao Liu and Yukun Yan and Huiyuan Xie and Yu Gu and Ge Yu and Maosong Sun}, | |
| year={2026}, | |
| eprint={2606.27786}, | |
| archivePrefix={arXiv}, | |
| primaryClass={cs.CL}, | |
| url={https://arxiv.org/abs/2606.27786}, | |
| } | |
| ``` |