Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2609.38186

Why and How People Check Generative AI Output for Mistakes

Patrick Gage Kelley·Derrick Feldmann·Reena Jana·Colleen Thompson-Kuhn·Allison Woodruff
View original source ↗Read source document ↗Export metadata ↓

Abstract

Generative AI output can contain errors, such as hallucinations, non-responsive results, or otherwise inaccurate or potentially harmful content. To explore the public's emerging understanding, attitudes, and behavior regarding such mistakes, we ran an online survey in the United States with 1,503 respondents, with a representative sample of the population. We report high public awareness of generative AI mistakes. Further, many respondents report checking generative AI output, for example, by comparing results with other online resources. We conclude with guidance for explanations and in-product disclosures about generative AI mistakes.

Explore related subjects

cs.HC

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Patrick Gage Kelley, Derrick Feldmann, Reena Jana, Colleen Thompson-Kuhn, Allison Woodruff. 2026-08-08. Why and How People Check Generative AI Output for Mistakes. https://arxiv.org/abs/2609.38186

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Before Bringing It Up: When and How AI Companions Should Use Memory

Memory can sustain AI companionship, yet even accurate recollection can be inappropriate to use. Two rounds of formative interviews with 14 users (n = 6 exploratory, n = 8 memory-focused) motivate asking what a companion should consider before using past information. Eight themes inform Reconsider, a single-call procedure with five checks and four handling modes, evaluated on 80 scenarios across five models over 400 blinded within-model pairs. Two LLM judges favored Reconsider by net margins of +15 and +23 percentage points, with bootstrap intervals excluding zero for three of five models but not for GPT or Claude. Evaluator analysis linked judge scoring differences to model family, and a preliminary matched-guidance control isolating memory-specific content gave positive margins. We contribute an interview-grounded design framework for memory use and an evaluation that scrutinizes its own evaluators.

cs.HC↗
arXiv2026

Intent Graph: Navigating the Analytical Reasoning Space for Exploratory Data Analysis

Exploratory data analysis (EDA) is rarely open-ended in practice: analysts work from high-level domain questions toward the concrete analyses that can answer them, prioritizing directions with domain knowledge and prior hypotheses. Large language models (LLMs) can supply such knowledge, but their responses are unstructured, leaving analysts no way to see what has been explored, what is missing, or why one direction was chosen over another. We present DAG-EDA, a system that lets analysts and an LLM co-navigate the space of possible analyses through two linked structures. An intent graph, governed by a grammar of analytical intent, decomposes an ambiguous natural-language question into progressively concrete analysis tasks, keeping alternative framings open and letting analysts branch, backtrack, and compare paths. A multi-layered knowledge graph externalizes the LLM's domain knowledge, linking domain concepts to the dataset variables that can measure them, so analysts can inspect and contest how their question is grounded in the data. Both graphs are constructed from only the dataset and the analyst's question, and the analyses the analyst reaches are rendered as interactive dashboards. We illustrate the system through a usage scenario and describe a user study design for examining whether the system scaffold analysts' reasoning and navigation.

cs.HC↗
arXiv2026

Magic Pen: Automatic Pen Mode Switching for Document Annotation

Traditional digital pen interfaces use menu buttons to change the pen mode, which results in time and cognitive load spent on round-trip interactions and mode errors from tapping small mode selection buttons. This work presents the Magic Pen, a technique which uses machine learning to automatically switch between digital pen modes without requiring explicit mode changes. Magic Pen is driven by an LSTM model trained on pen data collected from 27 participants across two studies and uses transfer learning to iteratively tune the model towards how a specific user annotates. Error mitigation techniques using a flick gesture or on-screen tap are incorporated to correct mode errors or remove a stroke quickly. We evaluated Magic Pen in a comparative study with 18 participants, followed by iterative improvements and a deployment study with 8 participants. Magic Pen was preferred compared to a conventional menu-based approach, and transfer learning allowed for greater model predictability and stability.

cs.HC↗