Derivation Prompting: A Logic-Based Method for Improving Retrieval-Augmented Generation
Researchers introduce Derivation Prompting, a logic-inspired prompting technique for the generation step of Retrieval-Augmented Generation (RAG). It constructs an interpretable derivation tree by systematically applying rules to initial hypotheses, reducing hallucinations and erroneous reasoning in knowledge-intensive tasks. A case study showed significant reduction in unacceptable answers compared to traditional RAG and long-context window methods.
[2605.14053] Derivation Prompting: A Logic-Based Method for Improving Retrieval-Augmented Generation
[Submitted on 13 May 2026]
Title:Derivation Prompting: A Logic-Based Method for Improving Retrieval-Augmented Generation
View a PDF of the paper titled Derivation Prompting: A Logic-Based Method for Improving Retrieval-Augmented Generation, by Ignacio Sastre and 2 other authors
View PDF HTML (experimental)
Abstract:The application of Large Language Models to Question Answering has shown great promise, but important challenges such as hallucinations and erroneous reasoning arise when using these models, particularly in knowledge-intensive, domain-specific tasks. To address these issues, we introduce Derivation Prompting, a novel prompting technique for the generation step of the Retrieval-Augmented Generation framework. Inspired by logic derivations, this method involves deriving conclusions from initial hypotheses through the systematic application of predefined rules. It constructs a derivation tree that is interpretable and adds control over the generation process. We applied this method in a specific case study, significantly reducing unacceptable answers compared to traditional RAG and long-context window methods.
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite as: arXiv:2605.14053 [cs.CL]
(or arXiv:2605.14053v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2605.14053
arXiv-issued DOI via DataCite (pending registration)
Journal reference: Advances in Artificial Intelligence IBERAMIA 2024, LNCS 15277, pp. 412 423, Springer (2025)
Related DOI:
https://doi.org/10.1007/978-3-031-80366-6_34
DOI(s) linking to related resources
Submission history
From: Ignacio Sastre [view email] [v1] Wed, 13 May 2026 19:20:16 UTC (2,249 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Derivation Prompting: A Logic-Based Method for Improving Retrieval-Augmented Generation, by Ignacio Sastre and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-05
Change to browse by:
cs cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)