Jungo Kasai, Ronan Le Bras, Yejin Choi, Hao Peng, Dragomir Radev, Noah Smith, Ximing Lu, Keisuke Sakaguchi
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.
Many language generation models are now available for a wide range of generation tasks, including machine translation and summarization. Combining such diverse models may lead to further progress, but ensembling generation models is challenging during inference: conventional ensembling methods (e.g., shallow fusion) require that the models share vocabulary/tokenization schemes. We introduce TWIST decoding, a simple and general text generation algorithm that benefits from diverse models at inference time. Our method does not assume the vocabulary, tokenization or even generation order is shared. Our extensive evaluations on machine translation and scientific paper summarization demonstrate that TWIST decoding substantially outperforms each model decoded in isolation over various scenarios, including cases where domainspecific and general-purpose models are both available. TWIST decoding also consistently outperforms the popular reranking heuristic where output candidates from one model are rescored by another. We hope that our work will encourage researchers and practitioners to examine generation models collectively, not just independently, and to seek out models with complementary strengths to the currently available models. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2205.09273")
get_code_for_paper("2205.09273")
have("2205.09273")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2205.09273.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2205.09273)
Connect an agent — have() is free.