SWI：大型語言模型中的意圖驅動對話

SWI: Speaking with Intent in Large Language Models

March 27, 2025

作者: Yuwei Yin, EunJeong Hwang, Giuseppe Carenini

cs.AI

摘要

意圖，通常明確制定並規劃，作為認知框架用於推理和問題解決。本文在大語言模型（LLMs）中引入了「意圖驅動對話」（Speaking with Intent, SWI）的概念，其中明確生成的意圖封裝了模型的潛在意圖，並提供高層次的規劃以指導後續的分析與溝通。通過模擬人類思維中的深思熟慮與目的性，SWI被假設能夠增強LLMs的推理能力與生成質量。在數學推理基準上的大量實驗一致證明了意圖驅動對話相較於基線（即無明確意圖的生成）的優越性。此外，SWI在答案觸發提示方法如「思維鏈」（Chain-of-Thought）和「計劃與解決」（Plan-and-Solve）上表現更佳，並與強力方法ARR（分析、檢索與推理）保持競爭力。同時，SWI在推理密集型的問答（QA）和文本摘要基準上的有效性和泛化能力也得到了鞏固，其中SWI為基線生成帶來了持續的改進。在文本摘要中，SWI生成的摘要展現出更高的準確性、簡潔性和事實正確性，且幻覺更少。此外，人工評估驗證了SWI產生意圖的連貫性、有效性和可解釋性。這項概念驗證研究為利用認知概念增強LLMs的推理能力開闢了一條新途徑。

English

Intent, typically clearly formulated and planned, functions as a cognitive framework for reasoning 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 communication. 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 mathematical reasoning benchmarks consistently demonstrate the superiority of Speaking with Intent over Baseline (i.e., generation without explicit intent). Moreover, SWI outperforms answer-trigger prompting methods Chain-of-Thought and Plan-and-Solve and maintains competitive performance with the strong method ARR (Analyzing, Retrieving, and Reasoning). Additionally, the effectiveness and generalizability of SWI are solidified on reasoning-intensive question answering (QA) and text summarization benchmarks, where SWI brings consistent improvement to the Baseline generation. In text summarization, SWI-generated summaries exhibit greater accuracy, conciseness, and factual correctness, with fewer hallucinations. Furthermore, human evaluations verify the coherence, effectiveness, and interpretability of the intent produced by SWI. This proof-of-concept study creates a novel avenue for enhancing LLMs' reasoning abilities with cognitive notions.