EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Mitigating Prompt-Induced Cognitive Biases in General-Purpose AI for Software Engineering

Francesco Sovrano, Gabriele Dominici, Alberto Bacchelli

Proceedings of the ACM on Software Engineering · 30.06.2026 · 3 (FSE) · 2419-2441

DOI: 10.1145/3808115 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Software Engineering, online erschienen am 30.06.2026. Verfasst von Francesco Sovrano und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Swiss National Science Foundation, Horizon Europe.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Prompt-induced cognitive biases are changes in a general-purpose AI (GPAI) system's decisions caused solely by biased wording in the input (e.g., framing, anchors), not task logic. In software engineering (SE) decision support (where problem statements and requirements are natural language) small phrasing shifts (e.g., popularity hints or outcome reveals) can push GPAI models toward suboptimal decisions. We study this with PROBE-SWE, a dynamic benchmark for SE that pairs biased and unbiased versions of the same SE dilemmas, controls for logic and difficulty, and targets eight SE-relevant biases (anchoring, availability, bandwagon, confirmation, framing, hindsight, hyperbolic discounting, overconfidence). We ask whether prompt engineering mitigates bias sensitivity in practice, focusing on actionable techniques that practitioners can apply off-the-shelf in real environments. Testing common strategies (e.g., chain-of-thought, self-debiasing) on cost-effective GPAI systems, we find no statistically significant reductions in bias sensitivity on a per-bias basis. We then adopt a Prolog-style view of the reasoning process: solving SE dilemmas requires making explicit any background axioms and inference assumptions (i.e., SE best practices) that are usually implicit in the prompt. So, we hypothesize that bias-inducing features short-circuit assumption elicitation, pushing GPAI models toward biased shortcuts. Building on this, we introduce an end-to-end method that elicits best practices and injects axiomatic reasoning cues into the prompt before answering, reducing overall bias sensitivity by 51% on average (p < .001). Finally, we report a thematic analysis that surfaces linguistic patterns associated with heightened bias sensitivity, clarifying when GPAI use is less advisable for SE decision support and where to focus future countermeasures.

Förderung

  • Swiss National Science Foundation
  • Horizon Europe

Zitieren

APA

Sovrano, F., Dominici, G., & Bacchelli, A. (2026). Mitigating Prompt-Induced Cognitive Biases in General-Purpose AI for Software Engineering. Proceedings of the ACM on Software Engineering, 3(FSE), 2419-2441. https://doi.org/10.1145/3808115

Vancouver

Sovrano F, Dominici G, Bacchelli A. Mitigating Prompt-Induced Cognitive Biases in General-Purpose AI for Software Engineering. Proceedings of the ACM on Software Engineering. 2026;3(FSE):2419-2441. doi:10.1145/3808115

BibTeX
@article{Sovrano2026,
  author = {Sovrano, Francesco and Dominici, Gabriele and Bacchelli, Alberto},
  title = {Mitigating Prompt-Induced Cognitive Biases in General-Purpose AI for Software Engineering},
  journal = {Proceedings of the ACM on Software Engineering},
  year = {2026},
  volume = {3},
  number = {FSE},
  pages = {2419--2441},
  doi = {10.1145/3808115}
}
Kostenlos starten →