Identifying High-Confidence Social Biases in LLMs for Trustworthy Conversational Tutoring Agents

• URL: http://arxiv.org/abs/2606.01584v1
• Date: Mon, 01 Jun 2026 02:28:27 GMT
• Title: Identifying High-Confidence Social Biases in LLMs for Trustworthy Conversational Tutoring Agents
• Abstract summary: We evaluate large language models (LLMs) in conversational tutoring scenarios to identify high-confidence social biases.<n>We present a new dataset generation method that enables bias evaluation under naturalistic instructional conditions.<n>We find that bias detection is substantially more challenging in conversational tutoring contexts than in benchmark-based evaluations.
• Score: 0.30079490585515334
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Conversational tutoring agents have been shown to improve learning engagement and student outcomes, and large language models (LLMs) are increasingly used in these systems to provide scalable, personalized feedback. However, LLMs may perpetuate or amplify stereotypical social biases, posing particular risks in educational settings. In this study, we evaluate LLMs in conversational tutoring scenarios to identify high-confidence social biases, instances where models are unable to identify biased judgments in tutoring conversations while maintaining strong confidence in their assessments, potentially affecting their reasoning and the feedback they provide to learners. We present a new dataset generation method that enables bias evaluation under naturalistic instructional conditions by regenerating student-AI tutor interactions and introducing turns with controlled bias derived from a benchmark dataset. Using this data, we assess multiple LLMs' ability to detect stereotypical biases and analyze the confidence and reasoning underlying their responses through computational and human evaluations. We find that bias detection is substantially more challenging in conversational tutoring contexts than in benchmark-based evaluations, and that state-of-the-art LLMs are overconfident in their incorrect assessments of stereotypical bias statements. Moreover, model confidence strongly influences reasoning and feedback, highlighting the risks of overconfident, biased behavior in LLM-based tutoring agents. We conclude by discussing implications, mitigation considerations, and directions for future research.

Related papers

• Evaluating from Benign to Dynamic Adversarial: A Squid Game for Large Language Models [57.33350664910483]
  We introduce Squid Game, a dynamic and adversarial evaluation environment with resource-constrained and asymmetric information settings.<n>We evaluate over 50 LLMs on Squid Game, presenting the largest behavioral evaluation study of general LLMs on dynamic adversarial scenarios.
  arXiv  Detail & Related papers  (2025-11-12T06:06:29Z)
• An Empirical Study of the Anchoring Effect in LLMs: Existence, Mechanism, and Potential Mitigations [12.481311145515706]
  We investigate the anchoring effect, a cognitive bias where the mind relies heavily on the first information as anchors to make affected judgments.<n>To facilitate studies at scale on the anchoring effect, we introduce a new dataset, SynAnchors.<n>Our findings show that LLMs' anchoring bias exists commonly with shallow-layer acting and is not eliminated by conventional strategies.
  arXiv  Detail & Related papers  (2025-05-21T11:33:54Z)
• LLM-Evaluation Tropes: Perspectives on the Validity of LLM-Evaluations [29.031539043555362]
  Large Language Models (LLMs) are increasingly used to evaluate information systems.<n>Recent studies suggest that LLM-based evaluations often align with human judgments.<n>This paper examines scenarios where LLM-evaluators may falsely indicate success.
  arXiv  Detail & Related papers  (2025-04-27T02:14:21Z)
• An Empirical Analysis of Uncertainty in Large Language Model Evaluations [28.297464655099034]
  We conduct experiments involving 9 widely used LLM evaluators across 2 different evaluation settings.<n>We pinpoint that LLM evaluators exhibit varying uncertainty based on model families and sizes.<n>We find that employing special prompting strategies, whether during inference or post-training, can alleviate evaluation uncertainty to some extent.
  arXiv  Detail & Related papers  (2025-02-15T07:45:20Z)
• Towards Understanding the Robustness of LLM-based Evaluations under Perturbations [9.944512689015998]
  Large Language Models (LLMs) can serve as automatic evaluators for non-standardized metrics in summarization and dialog-based tasks.<n>We conduct experiments across multiple prompting strategies to examine how LLMs fare as quality evaluators when compared with human judgments.
  arXiv  Detail & Related papers  (2024-12-12T13:31:58Z)
• CBEval: A framework for evaluating and interpreting cognitive biases in LLMs [1.4633779950109127]
  Large Language models exhibit notable gaps in their cognitive processes.<n>As reflections of human-generated data, these models have the potential to inherit cognitive biases.
  arXiv  Detail & Related papers  (2024-12-04T05:53:28Z)
• Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective [66.34066553400108]
  We conduct a rigorous evaluation of large language models' implicit bias towards certain demographics.<n>Inspired by psychometric principles, we propose three attack approaches, i.e., Disguise, Deception, and Teaching.<n>Our methods can elicit LLMs' inner bias more effectively than competitive baselines.
  arXiv  Detail & Related papers  (2024-06-20T06:42:08Z)
• Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning [61.2224355547598]
  Open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress. Our investigation exposes a critical oversight in this belief. By deploying carefully designed demonstrations, our research demonstrates that base LLMs could effectively interpret and execute malicious instructions.
  arXiv  Detail & Related papers  (2024-04-16T13:22:54Z)
• Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMs [6.090496490133132]
  We propose Reinforcement Learning from Multi-role Debates as Feedback (RLDF), a novel approach for bias mitigation replacing human feedback in traditional RLHF. We utilize LLMs in multi-role debates to create a dataset that includes both high-bias and low-bias instances for training the reward model in reinforcement learning.
  arXiv  Detail & Related papers  (2024-04-15T22:18:50Z)
• Evaluating Interventional Reasoning Capabilities of Large Language Models [58.52919374786108]
  Large language models (LLMs) are used to automate decision-making tasks.<n>In this paper, we evaluate whether LLMs can accurately update their knowledge of a data-generating process in response to an intervention.<n>We create benchmarks that span diverse causal graphs (e.g., confounding, mediation) and variable types.<n>These benchmarks allow us to isolate the ability of LLMs to accurately predict changes resulting from their ability to memorize facts or find other shortcuts.
  arXiv  Detail & Related papers  (2024-04-08T14:15:56Z)
• What Large Language Models Know and What People Think They Know [13.939511057660013]
  Large language models (LLMs) are increasingly integrated into decision-making processes.<n>To earn human trust, LLMs must be well calibrated so that they can accurately assess and communicate the likelihood of their predictions being correct.<n>Here we explore the calibration gap, which refers to the difference between human confidence in LLM-generated answers and the models' actual confidence, and the discrimination gap, which reflects how well humans and models can distinguish between correct and incorrect answers.
  arXiv  Detail & Related papers  (2024-01-24T22:21:04Z)
• Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty [53.336235704123915]
  We investigate how LMs incorporate confidence in responses via natural language and how downstream users behave in response to LM-articulated uncertainties. We find that LMs are reluctant to express uncertainties when answering questions even when they produce incorrect responses. We test the risks of LM overconfidence by conducting human experiments and show that users rely heavily on LM generations. Lastly, we investigate the preference-annotated datasets used in post training alignment and find that humans are biased against texts with uncertainty.
  arXiv  Detail & Related papers  (2024-01-12T18:03:30Z)
• Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
  We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools. Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions. Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
  arXiv  Detail & Related papers  (2023-09-20T09:23:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.