We lifted 3 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| eva-giboulot/watermax | canonical | 1 of 3 |
| Function | Status | Where it lives |
|---|---|---|
| generate_mmw_path | Ran | eva-giboulot/watermax/test_sentence_wm.py pointer only (licence: NONE) · get_code("2006c2f6f6daa764") |
| get_detector | Not yet run | eva-giboulot/watermax/test_sentence_wm.py pointer only (licence: NONE) · get_code("aa5abf5d87851c1c") |
| get_generator | Not yet run | eva-giboulot/watermax/test_sentence_wm.py pointer only (licence: NONE) · get_code("f59da376d411ca93") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Watermarking is a technical means to dissuade malfeasant usage of Large Language Models. This paper proposes a novel watermarking scheme, so-called WaterMax, that enjoys high detectability while sustaining the quality of the generated text of the original LLM. Its new design leaves the LLM untouched (no modification of the weights, logits, temperature, or sampling technique). WaterMax balances robustness and complexity contrary to the watermarking techniques of the literature inherently provoking a trade-off between quality and robustness. Its performance is both theoretically proven and experimentally validated. It outperforms all the SotA techniques under the most complete benchmark suite. Code available at https://github.com/eva-giboulot/WaterMax.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2403.04808")
get_code_for_paper("2403.04808")
have("2403.04808")
Connect an agent — have() is free.