Papers by Yasaman Jafari
MORL-Prompt: An Empirical Analysis of Multi-Objective Reinforcement Learning for Discrete Prompt Optimization (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Current RL-based prompt tuning techniques focus on maximizing the average of reward functions, which does not necessarily lead to prompts that achieve balance across rewards. |
| Approach: | They compare RL-based discrete prompt optimization techniques with a new set of target language models to find prompts that maximize an average of rewards. |
| Outcome: | The proposed methods perform better on two NLP tasks, style transfer and machine translation, and achieve a better balance of all rewards. |