# Do Large Language Models Need Intent? Revisiting Response Generation Strategies for Service Assistant

arXiv: https://arxiv.org/abs/2509.05006 · HTML: https://mlsanity.com/paper/2509.05006/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 7 references that are in the map.
- First posted on arXiv 5 Sep 2025.

## Builds on (most cited first, 5 of 5)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Can ChatGPT Detect Intent? Evaluating Large Language Models for Spoken Language Understanding](https://mlsanity.com/paper/2305.13512/) (2023)

## Built on by (most cited first, 2 of 2)

- [NC-Bench: An LLM Benchmark for Evaluating Conversational Competence](https://mlsanity.com/paper/2601.06426/) (2026)
- [Clinical Communication Processing with Models Trained on LLM-Generated Synthetic Data: A Structured Survey and Novel Application Case Studies](https://mlsanity.com/paper/2608.05993/) (2026)

## Abstract (arXiv)

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.