Dayeon Ki, Marine Carpuat
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Can we improve machine translation (MT) with LLMs by rewriting their inputs automatically? Users commonly rely on the intuition that wellwritten text is easier to translate when using off-the-shelf MT systems. LLMs can rewrite text in many ways but in the context of MT, these capabilities have been primarily exploited to rewrite outputs via post-editing. We present an empirical study of 21 input rewriting methods with 3 open-weight LLMs for translating from English into 6 target languages. We show that text simplification is the most effective MTagnostic rewrite strategy and that it can be improved further when using quality estimation to assess translatability. Human evaluation further confirms that simplified rewrites and their MT outputs both largely preserve the original meaning of the source and MT. These results suggest LLM-assisted input rewriting as a promising direction for improving translations. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2502.16682")
get_code_for_paper("2502.16682")
have("2502.16682")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2502.16682.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2502.16682)
Connect an agent — have() is free.