Do Large Language Models Need Intent? Revisiting Response Generation Strategies for Service Assistant
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912573070245888 |
|---|---|
| author | Bolshinsky, Inbal Kupiec, Shani Sasson, Almog Aperstein, Yehudit Apartsin, Alexander |
| author_facet | Bolshinsky, Inbal Kupiec, Shani Sasson, Almog Aperstein, Yehudit Apartsin, Alexander |
| contents | In the era of conversational AI, generating accurate and contextually appropriate service responses remains a critical challenge. A central question remains: Is explicit intent recognition a prerequisite for generating high-quality service responses, or can models bypass this step and produce effective replies directly? This paper conducts a rigorous comparative study to address this fundamental design dilemma. Leveraging two publicly available service interaction datasets, we benchmark several state-of-the-art language models, including a fine-tuned T5 variant, across both paradigms: Intent-First Response Generation and Direct Response Generation. Evaluation metrics encompass both linguistic quality and task success rates, revealing surprising insights into the necessity or redundancy of explicit intent modelling. Our findings challenge conventional assumptions in conversational AI pipelines, offering actionable guidelines for designing more efficient and effective response generation systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_05006 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Do Large Language Models Need Intent? Revisiting Response Generation Strategies for Service Assistant Bolshinsky, Inbal Kupiec, Shani Sasson, Almog Aperstein, Yehudit Apartsin, Alexander Computation and Language Machine Learning In the era of conversational AI, generating accurate and contextually appropriate service responses remains a critical challenge. A central question remains: Is explicit intent recognition a prerequisite for generating high-quality service responses, or can models bypass this step and produce effective replies directly? This paper conducts a rigorous comparative study to address this fundamental design dilemma. Leveraging two publicly available service interaction datasets, we benchmark several state-of-the-art language models, including a fine-tuned T5 variant, across both paradigms: Intent-First Response Generation and Direct Response Generation. Evaluation metrics encompass both linguistic quality and task success rates, revealing surprising insights into the necessity or redundancy of explicit intent modelling. Our findings challenge conventional assumptions in conversational AI pipelines, offering actionable guidelines for designing more efficient and effective response generation systems. |
| title | Do Large Language Models Need Intent? Revisiting Response Generation Strategies for Service Assistant |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2509.05006 |