EPS
← All batches·2605.14053

Derivation Prompting: A Logic-Based Method for Improving Retrieval-Augmented Generation

topic: current_projecttop score: 100released: 2026-05-15first surfaced: 2026-05-15arXivPDFlinked_to_results2026-05-15

Authors: Ignacio Sastre, Guillermo Moncecchi, Aiala Ros'a

arXiv · PDF

Summary

arXiv:2605. 14053v1 Announce Type: new 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.

Relevance

Read next because Derivation Prompting: A Logic-Based Method for Improving Retrieval-Augmented Generation overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ..., vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: text, eval, compare, control, language, model. Source: arxiv cs.CL (NLP).

Abstract

arXiv:2605.14053v1 Announce Type: new 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.