Fine-Grained Controllable Text Generation Using Non-Residual Prompting

The introduction of immensely large Causal Language Models (CLMs) has rejuvenated the interest in open-ended text generation. However, controlling the generative process for these Transformer-based models is at large an unsolved problem. Earlier work has explored either plug-and-play decoding strategies, or more powerful but blunt approaches such as prompting. There hence currently exists a trade-off between fine-grained control, and the capability for more expressive high-level instructions. To alleviate this trade-off, we propose an encoder-decoder architecture that enables intermediate text prompts at arbitrary time steps. We propose a resource-efficient method for converting a pre-trained CLM into this architecture, and demonstrate its potential on various experiments, including the novel task of contextualized word inclusion. Our method provides strong results on multiple experimental settings, proving itself to be both expressive and versatile.

Öhman, Joey (författare)
Liu, Fangyu (författare)
Verlinden, Severine (författare)
Nivre, Joakim,1962-RISE,Research Institutes of Sweden(Swepub:ri)joakim.nivre@ri.se (författare)
Sahlgren, Magnus (författare)
RISEDatavetenskap (creator_code:org_t)

Ingår i:Proceedings of the 60th Annual Meeting of the Association for Computational LinguisticsStroudsburg, PA, USA : Association for Computational Linguistics, s. 6837-68579781955917216

Av författaren/redakt...: Carlsson, Fredri ...; Öhman, Joey; Liu, Fangyu; Verlinden, Sever ...; Nivre, Joakim, 1 ...; Sahlgren, Magnus

Om ämnet

NATURVETENSKAP: NATURVETENSKAP; och Data och informa ...; och Språkteknologi

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.