Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing

Brief Instruction

Here is a brief instruction for the implementation of the paper Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing. We will update more details soon.

Data

You can download the data used in the paper at Google Drive

Direct Reproduction

You can refer to the Runner folder to check the bash for direct reproduction with you own environment and

pip install -r requirements.txt

Other Usage

You can download the data from Google Drive and use the intermediate data to do quick adaptation. If you have further questions or cooperation willings, please create new issues or email me