Human cognitive biases in software engineering can lead to costly errors. While general-purpose AI (GPAI) systems may help mitigate these biases due to their non-human nature, their training on human-generated data raises a critical question: Do GPAI systems themselves exhibit cognitive biases? To investigate this, we present the first dynamic benchmarking framework to evaluate data-induced cognitive biases in GPAI within software engineering workflows. Starting with a seed set of 16 hand-crafted realistic tasks, each featuring one of 8 cognitive biases (e.g., anchoring, framing) and corresponding unbiased variants, we test whether bias-inducing linguistic cues unrelated to task logic can lead GPAI systems from correct to incorrect conclusions. To scale the benchmark and ensure realism, we develop an on-demand augmentation pipeline relying on GPAI systems to generate task variants that preserve bias-inducing cues while varying surface details. This pipeline ensures correctness (88-99% on average, according to human evaluation), promotes diversity, and controls reasoning complexity by leveraging Prolog-based reasoning. We evaluate leading GPAI systems (GPT, LLaMA, DeepSeek) and find a consistent tendency to rely on shallow linguistic heuristics over more complex reasoning. All systems exhibit bias sensitivity (6-35%), which increases with task complexity (up to 49%) and highlights risks in AI-driven software engineering.

Large Language Models (LLMs) demonstrate impressive capabilities across a wide range of tasks, yet their safety mechanisms remain susceptible to adversarial attacks that exploit cognitive biases -- systematic deviations from rational judgment. Unlike prior jailbreaking approaches focused on prompt engineering or algorithmic manipulation, this work highlights the overlooked power of multi-bias interactions in undermining LLM safeguards. We propose CognitiveAttack, a novel red-teaming framework that systematically leverages both individual and combined cognitive biases. By integrating supervised fine-tuning and reinforcement learning, CognitiveAttack generates prompts that embed optimized bias combinations, effectively bypassing safety protocols while maintaining high attack success rates. Experimental results reveal significant vulnerabilities across 30 diverse LLMs, particularly in open-source models. CognitiveAttack achieves a substantially higher attack success rate compared to the SOTA black-box method PAP (60.1% vs. 31.6%), exposing critical limitations in current defense mechanisms. These findings highlight multi-bias interactions as a powerful yet underexplored attack vector. This work introduces a novel interdisciplinary perspective by bridging cognitive science and LLM safety, paving the way for more robust and human-aligned AI systems.

Large language models (LLMs) have shown potential in supporting decision-making applications, particularly as personal assistants in the financial, healthcare, and legal domains. While prompt engineering strategies have enhanced the capabilities of LLMs in decision-making, cognitive biases inherent to LLMs present significant challenges. Cognitive biases are systematic patterns of deviation from norms or rationality in decision-making that can lead to the production of inaccurate outputs. Existing cognitive bias mitigation strategies assume that input prompts only contain one type of cognitive bias, limiting their effectiveness in more challenging scenarios involving multiple cognitive biases. To fill this gap, we propose a cognitive debiasing approach, self-adaptive cognitive debiasing (SACD), that enhances the reliability of LLMs by iteratively refining prompts. Our method follows three sequential steps - bias determination, bias analysis, and cognitive debiasing - to iteratively mitigate potential cognitive biases in prompts. We evaluate SACD on finance, healthcare, and legal decision-making tasks using both open-weight and closed-weight LLMs. Compared to advanced prompt engineering methods and existing cognitive debiasing techniques, SACD achieves the lowest average bias scores in both single-bias and multi-bias settings.

Hallucination is a long-standing problem that has been actively investigated in Vision-Language Models (VLMs). Existing research commonly attributes hallucinations to technical limitations or sycophancy bias, where the latter means the models tend to generate incorrect answers to align with user expectations. However, these explanations primarily focus on technical or externally driven factors, and may have neglected the possibility that hallucination behaviours might mirror cognitive biases observed in human psychology. In this work, we introduce a psychological taxonomy, categorizing VLMs' cognitive biases that lead to hallucinations, including sycophancy, logical inconsistency, and a newly identified VLMs behaviour: appeal to authority. To systematically analyze these behaviours, we design AIpsych, a scalable benchmark that reveals psychological tendencies in model response patterns. Leveraging this benchmark, we investigate how variations in model architecture and parameter size influence model behaviour when responding to strategically manipulated questions. Our experiments reveal that as model size increases, VLMs exhibit stronger sycophantic tendencies but reduced authority bias, suggesting increasing competence but a potential erosion of response integrity. A human subject study further validates our hypotheses and highlights key behavioural differences between VLMs and human respondents. This work suggests a new perspective for understanding hallucination in VLMs and highlights the importance of integrating psychological principles into model evaluation. The benchmark and codes are tested and available in the anonymous link https://anonymous.4open.science/r/AIpsych-666.Figure 1: Left: a VLM exhibits sycophancy by favouring the questioner's options despite recognising it is a pink cup. Right: a human demonstrates authority bias by accepting the question's framing, also yielding the wrong answer. However, to distinguish between them, we will need to ask more questions. VLMs have made remarkable progress, achieving increasingly higher accuracy in visual reasoning tasks and enhancing real-world applications such as image captioning, visual question answering, and multimodal retrieval (Chen et al., 2023).

As Large Language Models (LLMs) are increasingly embedded in real-world decision-making processes, it becomes crucial to examine the extent to which they exhibit cognitive biases. Extensively studied in the field of psychology, cognitive biases appear as systematic distortions commonly observed in human judgments. This paper presents a large-scale evaluation of eight well-established cognitive biases across 45 LLMs, analyzing over 2.8 million LLM responses generated through controlled prompt variations. To achieve this, we introduce a novel evaluation framework based on multiple-choice tasks, hand-curate a dataset of 220 decision scenarios targeting fundamental cognitive biases in collaboration with psychologists, and propose a scalable approach for generating diverse prompts from human-authored scenario templates. Our analysis shows that LLMs exhibit bias-consistent behavior in 17.8-57.3% of instances across a range of judgment and decision-making contexts targeting anchoring, availability, confirmation, framing, interpretation, overattribution, prospect theory, and representativeness biases. We find that both model size and prompt specificity play a significant role on bias susceptibility as follows: larger size (>32B parameters) can reduce bias in 39.5% of cases, while higher prompt detail reduces most biases by up to 14.9%, except in one case (Overattribution), which is exacerbated by up to 8.8%.

Human-AI collaboration increasingly drives decision-making across industries, from medical diagnosis to content moderation. While AI systems promise efficiency gains by providing automated suggestions for human review, these workflows can trigger cognitive biases that degrade performance. We know little about the psychological factors that determine when these collaborations succeed or fail. We conducted a randomized experiment with 2,784 participants to examine how task design and individual characteristics shape human responses to AI-generated suggestions. Using a controlled annotation task, we manipulated three factors: AI suggestion quality in the first three instances, task burden through required corrections, and performance-based financial incentives. We collected demographics, attitudes toward AI, and behavioral data to assess four performance metrics: accuracy, correction activity, overcorrection, and undercorrection. Two patterns emerged that challenge conventional assumptions about human-AI collaboration. First, requiring corrections for flagged AI errors reduced engagement and increased the tendency to accept incorrect suggestions, demonstrating how cognitive shortcuts influence collaborative outcomes. Second, individual attitudes toward AI emerged as the strongest predictor of performance, surpassing demographic factors. Participants skeptical of AI detected errors more reliably and achieved higher accuracy, while those favorable toward automation exhibited dangerous overreliance on algorithmic suggestions. The findings reveal that successful human-AI collaboration depends not only on algorithmic performance but also on who reviews AI outputs and how review processes are structured. Effective human-AI collaborations require consideration of human psychology: selecting diverse evaluator samples, measuring attitudes, and designing workflows that counteract cognitive biases.

Continual Relation Extraction (CRE) aims to continually learn new emerging relations while avoiding catastrophic forgetting. Existing CRE methods mainly use memory replay and contrastive learning to mitigate catastrophic forgetting. However, these methods do not attach importance to the error cases that can reveal the model's cognitive biases more effectively. To address this issue, we propose an instruction-based continual contrastive tuning approach for Large Language Models (LLMs) in CRE. Different from existing CRE methods that typically handle the training and memory data in a unified manner, this approach splits the training and memory data of each task into two parts respectively based on the correctness of the initial responses and treats them differently through dual-task fine-tuning. In addition, leveraging the advantages of LLM's instruction-following ability, we propose a novel instruction-based contrastive tuning strategy for LLM to continuously correct current cognitive biases with the guidance of previous data in an instruction-tuning manner, which mitigates the gap between old and new relations in a more suitable way for LLMs. We experimentally evaluate our model on TACRED and FewRel, and the results show that our model achieves new state-of-the-art CRE performance with significant improvements, demonstrating the importance of specializing in exploiting error cases.

Using code generation as a case study, we find that OpenAI's

Application systems using natural language interfaces to databases (NLIDBs) have democratized data analysis. This positive development has also brought forth an urgent challenge to help users who might use these systems without a background in statistical analysis to formulate bias-free analytical questions. Although significant research has focused on text-to-SQL generation accuracy, addressing cognitive biases in analytical questions remains underexplored. We present VeriMinder, https://veriminder.ai, an interactive system for detecting and mitigating such analytical vulnerabilities. Our approach introduces three key innovations: (1) a contextual semantic mapping framework for biases relevant to specific analysis contexts (2) an analytical framework that operationalizes the Hard-to-Vary principle and guides users in systematic data analysis (3) an optimized LLM-powered system that generates high-quality, task-specific prompts using a structured process involving multiple candidates, critic feedback, and self-reflection. User testing confirms the merits of our approach. In direct user experience evaluation, 82.5% participants reported positively impacting the quality of the analysis. In comparative evaluation, VeriMinder scored significantly higher than alternative approaches, at least 20% better when considered for metrics of the analysis's concreteness, comprehensiveness, and accuracy. Our system, implemented as a web application, is set to help users avoid "wrong question" vulnerability during data analysis. VeriMinder code base with prompts, https://reproducibility.link/veriminder, is available as an MIT-licensed open-source software to facilitate further research and adoption within the community.

Large language models (LLMs) exhibit cognitive biases -- systematic tendencies of irrational decision-making, similar to those seen in humans. Prior work has found that these biases vary across models and can be amplified by instruction tuning. However, it remains unclear if these differences in biases stem from pretraining, finetuning, or even random noise due to training stochasticity. We propose a two-step causal experimental approach to disentangle these factors. First, we finetune models multiple times using different random seeds to study how training randomness affects over $30$ cognitive biases. Second, we introduce \emph{cross-tuning} -- swapping instruction datasets between models to isolate bias sources. This swap uses datasets that led to different bias patterns, directly testing whether biases are dataset-dependent. Our findings reveal that while training randomness introduces some variability, biases are mainly shaped by pretraining: models with the same pretrained backbone exhibit more similar bias patterns than those sharing only finetuning data. These insights suggest that understanding biases in finetuned models requires considering their pretraining origins beyond finetuning effects. This perspective can guide future efforts to develop principled strategies for evaluating and mitigating bias in LLMs.