Adding a fine-tuned intent recognition step before response generation improves automatic quality scores on two customer-service datasets, but the results are reported without statistical or human validation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Do Large Language Models Need Intent? Revisiting Response Generation Strategies for Service Assistant
Adding a fine-tuned intent recognition step before response generation improves automatic quality scores on two customer-service datasets, but the results are reported without statistical or human validation.