paper-with-me

홈 › Papers

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

2025-09-05 · Inbal Bolshinsky, Shani Kupiec, Almog Sasson, Yehudit Aperstein, Alexander Apartsin 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.

📄 PDF Abstract BibTeX arXiv:2509.05006

Code (0)

등록된 구현이 없습니다.

Tasks

Response GenerationIntent Recognition

Similar Papers 제목 키워드 기반

Is the Pope Catholic? Yes, the Pope is Catholic. Generative Evaluation of Non-Literal Intent Resolution in LLMs

2024-05-14 · Akhila Yerukola, Saujas Vaduguru, Daniel Fried, Maarten Sap

Humans often express their communicative intents indirectly or non-literally, which requires their interlocutors -- human or AI -- to understand beyond the literal meaning of words. While most existing work has focused o…

Intent-Aware Self-Correction for Mitigating Social Biases in Large Language Models

2025-03-08 · Panatchakorn Anantaprayoon, Masahiro Kaneko, Naoaki Okazaki

Self-Correction based on feedback improves the output quality of Large Language Models (LLMs). Moreover, as Self-Correction functions like the slow and conscious System-2 thinking from cognitive psychology's perspective,…

Response Generation

IPQA: A Benchmark for Core Intent Identification in Personalized Question Answering

2025-10-27 · Jieyong Kim, Maryam Amirizaniani, Soojin Yoon, Dongha Lee arxiv

Intent identification serves as the foundation for generating appropriate responses in personalized question answering (PQA). However, existing benchmarks evaluate only response quality or retrieval performance without d…

Question AnsweringAnswer Selection

Revisiting the Predictability of Language: Response Completion in Social Media

2012-07-01 · EMNLP 2012 7 · Bo Pang, Sujith Ravi

The Outputs of Large Language Models are Meaningless

2025-09-26 · Anandi Hattiangadi, Anders J. Schoubye arxiv

In this paper, we offer a simple argument for the conclusion that the outputs of large language models (LLMs) are meaningless. Our argument is based on two key premises: (a) that certain kinds of intentions are needed in…