# Behavioral Indicators of Overreliance During Interaction with Conversational Language Models

arXiv: https://arxiv.org/abs/2602.11567 · HTML: https://mlsanity.com/paper/2602.11567/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2026.

## Built on by (most cited first, 5 of 5)

- [Offloading Score: Measuring AI Reliance Through Counterfactual Workflows](https://mlsanity.com/paper/2605.29392/) (2026)
- [TutorTrace: A Dataset and Taxonomy for Classifying Learner Behavioral States during AI-Assisted Programming Education](https://mlsanity.com/paper/2608.26184/) (2026)
- [Towards Cognitive Process-Aware Proactive Writing Support](https://mlsanity.com/paper/2608.30424/) (2026)
- [Does AI Assistance Leave a Temporal Fingerprint? Detecting Overreliance in AI-Assisted Writing and Programming](https://mlsanity.com/paper/2609.17883/) (2026)
- [Generative Tutorial: Towards Live Contextualized Visual Instructions for Physical Tasks](https://mlsanity.com/paper/2609.24955/) (2026)

## Abstract (arXiv)

LLMs are now embedded in a wide range of everyday scenarios. However, their inherent hallucinations risk hiding misinformation in fluent responses, raising concerns about overreliance on AI. Detecting overreliance is challenging, as it often arises in complex, dynamic contexts and cannot be easily captured by post-hoc task outcomes. In this work, we aim to investigate how users' behavioral patterns correlate with overreliance. We collected interaction logs from 77 participants working with an LLM injected plausible misinformation across three real-world tasks and we assessed overreliance by whether participants detected and corrected these errors. By semantically encoding and clustering segments of user interactions, we identified five behavioral patterns linked to overreliance: users with low overreliance show careful task comprehension and fine-grained navigation; users with high overreliance show frequent copy-paste, skipping initial comprehension, repeated LLM references, coarse locating, and accepting misinformation despite hesitation. We discuss design implications for mitigation.