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

arXiv: https://arxiv.org/abs/2604.16756 · HTML: https://mlsanity.com/paper/2604.16756/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 63 references that are in the map.
- First posted on arXiv 18 Apr 2026.

## Builds on (most cited first, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://mlsanity.com/paper/2103.00453/) (2021)
- [An Empirical Study of the Non-determinism of ChatGPT in Code Generation](https://mlsanity.com/paper/2308.02828/) (2023)
- [Explanations Can Reduce Overreliance on AI Systems During Decision-Making](https://mlsanity.com/paper/2212.06823/) (2022)
- [Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics](https://mlsanity.com/paper/2410.21272/) (2024)
- [LLM-in-the-loop: Leveraging Large Language Model for Thematic Analysis](https://mlsanity.com/paper/2310.15100/) (2023)
- [In Search of Verifiability: Explanations Rarely Enable Complementary Performance in AI-Advised Decision Making](https://mlsanity.com/paper/2305.07722/) (2023)
- [Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models](https://mlsanity.com/paper/2405.10431/) (2024)
- [A Comprehensive Empirical Study of Bias Mitigation Methods for Machine Learning Classifiers](https://mlsanity.com/paper/2207.03277/) (2022)
- [Take Care of Your Prompt Bias! Investigating and Mitigating Prompt Bias in Factual Knowledge Extraction](https://mlsanity.com/paper/2403.09963/) (2024)
- [DevGPT: Studying Developer-ChatGPT Conversations](https://mlsanity.com/paper/2309.03914/) (2023)
- [Cognitive Biases in Software Engineering: A Systematic Mapping Study](https://mlsanity.com/paper/1707.03869/) (2017)
- [LLMs' Reshaping of People, Processes, Products, and Society in Software Development: A Comprehensive Exploration with Early Adopters](https://mlsanity.com/paper/2503.05012/) (2025)
- [DR.GAP: Mitigating Bias in Large Language Models using Gender-Aware Prompting with Decoupled Reasoning](https://mlsanity.com/paper/2502.11603/) (2025)
- [Is General-Purpose AI Reasoning Sensitive to Data-Induced Cognitive Biases? Dynamic Benchmarking on Typical Software Engineering Dilemmas](https://mlsanity.com/paper/2508.11278/) (2025)
- [Psycholinguistic Analyses in Software Engineering Text: A Systematic Literature Review](https://mlsanity.com/paper/2503.05992/) (2025)

## Built on by (most cited first, 1 of 1)

- [Security and Privacy in Agentic AI: Grand Challenges and Future Directions](https://mlsanity.com/paper/2607.06608/) (2026)

## Abstract (arXiv)

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.