# Trapped by Expectations: Functional Fixedness in LLM-Enabled Chat Search

arXiv: https://arxiv.org/abs/2504.02074 · HTML: https://mlsanity.com/paper/2504.02074/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 107 references that are in the map.
- First posted on arXiv 2 Apr 2025.

## Builds on (most cited first, 16 of 16)

- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [Evaluating Large Language Models in Theory of Mind Tasks](https://mlsanity.com/paper/2302.02083/) (2023)
- [Large language models in healthcare and medical domain: A review](https://mlsanity.com/paper/2401.06775/) (2023)
- [Cognitive Bias in Decision-Making with LLMs](https://mlsanity.com/paper/2403.00811/) (2024)
- [Deciding Fast and Slow: The Role of Cognitive Biases in AI-assisted Decision-making](https://mlsanity.com/paper/2010.07938/) (2020)
- [Analyzing and Characterizing User Intent in Information-seeking Conversations](https://mlsanity.com/paper/1804.08759/) (2018)
- [AI Can Be Cognitively Biased: An Exploratory Study on Threshold Priming in LLM-Based Batch Relevance Assessment](https://mlsanity.com/paper/2409.16022/) (2024)
- [User Intent Recognition and Satisfaction with Large Language Models: A User Study with ChatGPT](https://mlsanity.com/paper/2402.02136/) (2024)
- [Task Supportive and Personalized Human-Large Language Model Interaction: A User Study](https://mlsanity.com/paper/2402.06170/) (2024)
- [Exploring a Behavioral Model of "Positive Friction" in Human-AI Interaction](https://mlsanity.com/paper/2402.09683/) (2024)
- [Studying the Effects of Cognitive Biases in Evaluation of Conversational Agents](https://mlsanity.com/paper/2002.07927/) (2020)
- [Cognitively Biased Users Interacting with Algorithmically Biased Results in Whole-Session Search on Debated Topics](https://mlsanity.com/paper/2403.17286/) (2024)
- [Decoy Effect In Search Interaction: Understanding User Behavior and Measuring System Vulnerability](https://mlsanity.com/paper/2403.18462/) (2024)
- [Towards Detecting and Mitigating Cognitive Bias in Spoken Conversational Search](https://mlsanity.com/paper/2405.12480/) (2024)
- [Can Users Detect Biases or Factual Errors in Generated Responses in Conversational Information-Seeking?](https://mlsanity.com/paper/2410.21529/) (2024)
- [The Decoy Dilemma in Online Medical Information Evaluation: A Comparative Study of Credibility Assessments by LLM and Human Judges](https://mlsanity.com/paper/2411.15396/) (2024)

## Built on by (most cited first, 3 of 3)

- ["If You're Very Clever, No One Knows You've Used It": The Social Dynamics of Developing Generative AI Literacy in the Workplace](https://mlsanity.com/paper/2602.01386/) (2026)
- [Understanding Usage and Engagement in AI-Powered Scientific Research Tools: The Asta Interaction Dataset](https://mlsanity.com/paper/2602.23335/) (2026)
- [Not All Transparency Is Equal: Source Presentation Effects on Attention, Interaction, and Persuasion in Conversational Search](https://mlsanity.com/paper/2512.12207/) (2025)

## Abstract (arXiv)

Functional fixedness, a cognitive bias that restricts users' interactions with a new system or tool to expected or familiar ways, limits the full potential of Large Language Model (LLM)-enabled chat search, especially in complex and exploratory tasks. To investigate its impact, we conducted a crowdsourcing study with 450 participants, each completing one of six decision-making tasks spanning public safety, diet and health management, sustainability, and AI ethics. Participants engaged in a multi-prompt conversation with ChatGPT to address the task, allowing us to compare pre-chat intent-based expectations with observed interactions. We found that: 1) Several aspects of pre-chat expectations are closely associated with users' prior experiences with ChatGPT, search engines, and virtual assistants; 2) Prior system experience shapes language use and prompting behavior. Frequent ChatGPT users reduced deictic terms and hedge words and frequently adjusted prompts. Users with rich search experience maintained structured, less-conversational queries with minimal modifications. Users of virtual assistants favored directive, command-like prompts, reinforcing functional fixedness; 3) When the system failed to meet expectations, participants generated more detailed prompts with increased linguistic diversity, reflecting adaptive shifts. These findings suggest that while preconceived expectations constrain early interactions, unmet expectations can motivate behavioral adaptation. With appropriate system support, this may promote broader exploration of LLM capabilities. This work also introduces a typology for user intents in chat search and highlights the importance of mitigating functional fixedness to support more creative and analytical use of LLMs.