Integrating reasoning into large language models: A major step toward truthful AI

Nguyen Duc Xuan (), Pham Van Khanh (), Do Thi Loan () and Le Thi Thuy Giang ()

Edelweiss Applied Science and Technology, 2025, vol. 9, issue 7, 1072-1090

Abstract: This study investigates the approach of integrating reasoning into the outputs of large language models (LLMs) — combining logical inference techniques with knowledge retrieval — to enhance their alignment with truth. We begin by analyzing the statistical foundations of LLMs, which operate as probabilistic text generators based on Markovian assumptions without genuine semantic understanding. Next, we discuss the conceptual framework of 'truth' in the AI context, differentiating between descriptive truth (objective correctness), pragmatic truth (contextual utility), and verifiable knowledge (information supported by independent evidence). We examine advanced reasoning techniques — from Chain-of-Thought [1], Tree-of-Thought [2], Retrieval -Augmented Generation [3], to self-critique models like CriticGPT [4] - that move LLMs closer to verified knowledge and mitigate hallucination tendencies. The paper also explores the philosophical implications: Can modern LLMs, equipped with reasoning capacities, be considered 'fallible cognitive agents' - akin to humans in their capacity for error correction and learning -or are they merely stochastic parrots mimicking language without true understanding? Finally, we open a discussion on the risks, limitations, and ethical issues involved in deploying reasoning-integrated AI systems, connecting them with contemporary philosophical currents such as pragmatism, anti-realism, and behaviorist perspectives in evaluating artificial intelligence.

Keywords: Chain-of-thought; Epistemic and ethical AI; Large language models; Reasoning Integration; Retrieval-augmented generation; Tree-of-thought; Truthfulness in AI. (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://learning-gate.com/index.php/2576-8484/article/view/8810/2943 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ajp:edwast:v:9:y:2025:i:7:p:1072-1090:id:8810

Access Statistics for this article

More articles in Edelweiss Applied Science and Technology from Learning Gate
Bibliographic data for series maintained by Melissa Fernandes ().