SWI: Speaking with Intent in Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yin, Yuwei, Hwang, EunJeong, Carenini, Giuseppe
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914031667773440
author Yin, Yuwei
Hwang, EunJeong
Carenini, Giuseppe
author_facet Yin, Yuwei
Hwang, EunJeong
Carenini, Giuseppe
contents Intent, typically clearly formulated and planned, functions as a cognitive framework for communication and problem-solving. This paper introduces the concept of Speaking with Intent (SWI) in large language models (LLMs), where the explicitly generated intent encapsulates the model's underlying intention and provides high-level planning to guide subsequent analysis and action. By emulating deliberate and purposeful thoughts in the human mind, SWI is hypothesized to enhance the reasoning capabilities and generation quality of LLMs. Extensive experiments on text summarization, multi-task question answering, and mathematical reasoning benchmarks consistently demonstrate the effectiveness and generalizability of Speaking with Intent over direct generation without explicit intent. Further analysis corroborates the generalizability of SWI under different experimental settings. Moreover, human evaluations verify the coherence, effectiveness, and interpretability of the intent produced by SWI. The promising results in enhancing LLMs with explicit intents pave a new avenue for boosting LLMs' generation and reasoning abilities with cognitive notions.
format Preprint
id arxiv_https___arxiv_org_abs_2503_21544
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SWI: Speaking with Intent in Large Language Models
Yin, Yuwei
Hwang, EunJeong
Carenini, Giuseppe
Computation and Language
Artificial Intelligence
Machine Learning
I.2.7
Intent, typically clearly formulated and planned, functions as a cognitive framework for communication and problem-solving. This paper introduces the concept of Speaking with Intent (SWI) in large language models (LLMs), where the explicitly generated intent encapsulates the model's underlying intention and provides high-level planning to guide subsequent analysis and action. By emulating deliberate and purposeful thoughts in the human mind, SWI is hypothesized to enhance the reasoning capabilities and generation quality of LLMs. Extensive experiments on text summarization, multi-task question answering, and mathematical reasoning benchmarks consistently demonstrate the effectiveness and generalizability of Speaking with Intent over direct generation without explicit intent. Further analysis corroborates the generalizability of SWI under different experimental settings. Moreover, human evaluations verify the coherence, effectiveness, and interpretability of the intent produced by SWI. The promising results in enhancing LLMs with explicit intents pave a new avenue for boosting LLMs' generation and reasoning abilities with cognitive notions.
title SWI: Speaking with Intent in Large Language Models
topic Computation and Language
Artificial Intelligence
Machine Learning
I.2.7
url https://arxiv.org/abs/2503.21544