FF-BPSN combines forward and backward planning in a pseudo-siamese transformer setup with forward emphasis to achieve SOTA dialogue path planning on DuRecDial datasets and improve target-oriented response generation.
Language models are unsu- pervised multitask learners,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2verdicts
UNVERDICTED 2representative citing papers
A new prompting strategy for multi-turn dialogues improves core information filtering by 32.6% and QA accuracy by 14.1% on HotpotQA while reducing inference time by 73.1% and tokens by 59.4%.
citing papers explorer
-
Pseudo-Siamese Network for Planning in Target-Oriented Proactive Dialogues
FF-BPSN combines forward and backward planning in a pseudo-siamese transformer setup with forward emphasis to achieve SOTA dialogue path planning on DuRecDial datasets and improve target-oriented response generation.
-
A State-Update Prompting Strategy for Efficient and Robust Multi-turn Dialogue
A new prompting strategy for multi-turn dialogues improves core information filtering by 32.6% and QA accuracy by 14.1% on HotpotQA while reducing inference time by 73.1% and tokens by 59.4%.