# Hide or Highlight: Understanding the Impact of Factuality Expression on User Trust

arXiv: https://arxiv.org/abs/2508.07095 · HTML: https://mlsanity.com/paper/2508.07095/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 55 references that are in the map.
- First posted on arXiv 9 Aug 2025.

## Builds on (most cited first, 23 of 23)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [Language Models with Conformal Factuality Guarantees](https://mlsanity.com/paper/2402.10978/) (2024)
- [Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty](https://mlsanity.com/paper/2011.07586/) (2020)
- [Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty](https://mlsanity.com/paper/2401.06730/) (2024)
- [Generating Scientific Claims for Zero-Shot Scientific Fact Checking](https://mlsanity.com/paper/2203.12990/) (2022)
- [Investigating Explainability of Generative AI for Code through Scenario-based Design](https://mlsanity.com/paper/2202.04903/) (2022)
- [Comparing Traditional and LLM-based Search for Consumer Choice: A Randomized Experiment](https://mlsanity.com/paper/2307.03744/) (2023)
- [RELIC: Investigating Large Language Model Responses using Self-Consistency](https://mlsanity.com/paper/2311.16842/) (2023)
- [Atomic Fact Decomposition Helps Attributed Question Answering](https://mlsanity.com/paper/2410.16708/) (2024)
- [Show or Suppress? Managing Input Uncertainty in Machine Learning Model Explanations](https://mlsanity.com/paper/2101.09498/) (2021)
- [Designing for Appropriate Reliance: The Roles of AI Uncertainty Presentation, Initial User Decision, and User Demographics in AI-Assisted Decision-Making](https://mlsanity.com/paper/2401.05612/) (2024)
- [Multi-Level Explanations for Generative Language Models](https://mlsanity.com/paper/2403.14459/) (2024)
- [Trust and Reliance in XAI -- Distinguishing Between Attitudinal and Behavioral Measures](https://mlsanity.com/paper/2203.12318/) (2022)
- [Facilitating Human-LLM Collaboration through Factuality Scores and Source Attributions](https://mlsanity.com/paper/2405.20434/) (2024)
- [EvalAssist: A Human-Centered Tool for LLM-as-a-Judge](https://mlsanity.com/paper/2507.02186/) (2025)
- [Citations as Queries: Source Attribution Using Language Models as Rerankers](https://mlsanity.com/paper/2306.17322/) (2023)

## Built on by (most cited first, 1 of 1)

- [Full Disclosure, Less Trust? How the Level of Detail about AI Use in News Writing Affects Readers' Trust](https://mlsanity.com/paper/2601.09620/) (2026)

## Abstract (arXiv)

Large language models are known to produce outputs that are plausible but factually incorrect. To prevent people from making erroneous decisions by blindly trusting AI, researchers have explored various ways of communicating factuality estimates in AI-generated outputs to end-users. However, little is known about whether revealing content estimated to be factually incorrect influences users' trust when compared to hiding it altogether. We tested four different ways of disclosing an AI-generated output with factuality assessments: transparent (highlights less factual content), attention (highlights factual content), opaque (removes less factual content), ambiguity (makes less factual content vague), and compared them with a baseline response without factuality information. We conducted a human subjects research (N = 148) using the strategies in question-answering scenarios. We found that the opaque and ambiguity strategies led to higher trust while maintaining perceived answer quality, compared to the other strategies. We discuss the efficacy of hiding presumably less factual content to build end-user trust.