Predicting LLM Performance from Prompt Linguistic Features: An Empirical Study in Requirements Engineering

[2608.27621] Predicting LLM Performance from Prompt Linguistic Features: An Empirical Study in Requirements Engineering Skip to main content Search Submit Donate Log in Computer Science > Software Engineering arXiv:2608.27621 (cs) [Submitted on 27 Aug 2026] Title: Predicting LLM Performance from Prompt Linguistic Features: An Empirical Study in Requirements Engineering Authors: Quim Motger , Alessio Miaschi , Xavier Franch , Mohammad Amin Zadenoori , Alessio Ferrari View PDF HTML (experimental) Abstract: Background. LLM outputs are highly sensitive to prompt formulation: small wording changes can substantially affect output quality. This matters in software engineering, where prompts guide requirements analysis, code generation, and artefact synthesis. Poor formulations yield unreliable artefacts, yet practitioners lack principled ways to assess a prompt before inference, making selection depend on costly LLM calls and trial-and-error refinement. Aims. We investigate whether measurable linguistic properties of prompts can predict LLM performance before inference, enabling low-cost prompt selection and refinement, validated on binary requirements classification targeting F1, F2, precision, and recall. Method. We generate 9,000 linguistically controlled prompt variants from 100 initial prompts by varying 30 linguistic metrics, evaluated with five open-source LLMs on 625 annotated requirements. Regression predictors are trained via stratified 10-fold cross-validation with permutation-based significance testing; feature importance analysis identifies cross-LLM and model-specific predictors. Results. Linguistic features significantly predict prompt performance across all targets (R2 in [0.38,0.42], q<0.05). Syntactic and morphosyntactic features drive most predictive signal; cross-LLM predictors include compound dependency distribution, conjunction density, and word/sentence length, reflecting sensitivity to domain vocabulary and complex structures. Conclusions. Results suggest practical implications for prompt engineering, including overlap between linguistic patterns that reduce LLM performance and those that increase human comprehension difficulty, and the irrelevance of lexical variety as a quality dimension. More broadly, linguistic profiling combined with standard regression provides an effective, interpretable, low-cost prior before costly optimisation pipelines. Subjects: Software Engineering (cs.SE) Cite as: arXiv:2608.27621 [cs.SE] (or arXiv:2608.27621v1 [cs.SE] for this version) https://doi.org/10.48550/arXiv.2608.27621 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Quim Motger [ view email ] [v1] Thu, 27 Aug 2026 19:02:09 UTC (1,112 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.SE < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark 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? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• Predicting LLM Performance from Prompt Linguistic Features: An Empirical Study in Requirements Engineering#779549
• LangChoiceBench: Measuring and Explaining Programming-Language Choice in LLMs#432595
• EXPLORING HUMAN FACTORS IN LARGE LANGUAGE MODEL-ASSISTED SOFTWARE REQUIREMENTS SPECIFICATION#191278
• Predicting LLM Performance from Prompt Linguistic Features: An Empirical Study in Requirements Engineering#618642
• ProcArena: A Multi-Scenario Benchmark for LLMs on Direct and Interactive PL/SQL Development from Natural Language#974096