About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Timo Schick
- sl:arxiv_num : 2208.11663
- sl:arxiv_published : 2022-08-24T16:56:47Z
- sl:arxiv_summary : Textual content is often the output of a collaborative writing process: We
start with an initial draft, ask for suggestions, and repeatedly make changes.
Agnostic of this process, today's language models are trained to generate only
the final result. As a consequence, they lack several abilities crucial for
collaborative writing: They are unable to update existing texts, difficult to
control and incapable of verbally planning or explaining their actions. To
address these shortcomings, we introduce PEER, a collaborative language model
that is trained to imitate the entire writing process itself: PEER can write
drafts, add suggestions, propose edits and provide explanations for its
actions. Crucially, we train multiple instances of PEER able to infill various
parts of the writing process, enabling the use of self-training techniques for
increasing the quality, amount and diversity of training data. This unlocks
PEER's full potential by making it applicable in domains for which no edit
histories are available and improving its ability to follow instructions, to
write useful comments, and to explain its actions. We show that PEER achieves
strong performance across various domains and editing tasks.@en
- sl:arxiv_title : PEER: A Collaborative Language Model@en
- sl:arxiv_updated : 2022-08-24T16:56:47Z
- sl:bookmarkOf : https://arxiv.org/abs/2208.11663
- sl:creationDate : 2022-08-26
- sl:creationTime : 2022-08-26T01:42:05Z
Documents with similar tags (experimental)