Post

We got one paper accepted to #COLING2025: "MOPO: Multi-objective prompt optimization for affective text generation." with @romanklinger.de and Yarik Menchaca Resendiz. We optimize prompts for multiple objectives, while indirectly optimizing the prompts that optimize the prompts #NLP #NLProc (1/3)

2/12/24, 8:44 am0 reposts4 likes

BamNLP

@bamnlp.de

2 Dec 2024

This leads to more robust prompts, because we can, a posteriori, decide for which objective a prompt should work, without retraining. We focus our evaluation on affective text generation across multiple domains, but it should work across other multi-objective use cases (2/3).

BamNLP

@bamnlp.de

2 Dec 2024

We will share the preprint as soon as it's ready. (3/3)

BamNLP

@bamnlp.de

18 Dec 2024

Here comes the preprint: arxiv.org/abs/2412.12948

arxiv.orgMOPO: Multi-Objective Prompt Optimization for Affective Text GenerationHow emotions are expressed depends on the context and domain. On X (formerly Twitter), for instance, an author might simply use the hashtag #anger, while in a news headline, emotions are typically wri...