# Facilitating Human-LLM Collaboration through Factuality Scores and Source Attributions

arXiv: https://arxiv.org/abs/2405.20434 · HTML: https://mlsanity.com/paper/2405.20434/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 48 references that are in the map.
- First posted on arXiv 30 May 2024.

## Builds on (most cited first, 15 of 15)

- [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)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization](https://mlsanity.com/paper/2111.09525/) (2021)
- [RARR: Researching and Revising What Language Models Say, Using Language Models](https://mlsanity.com/paper/2210.08726/) (2022)
- [Questioning the AI: Informing Design Practices for Explainable AI User Experiences](https://mlsanity.com/paper/2001.02478/) (2020)
- [AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap](https://mlsanity.com/paper/2306.01941/) (2023)
- [Interpreting Language Models with Contrastive Explanations](https://mlsanity.com/paper/2202.10419/) (2022)
- [Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection](https://mlsanity.com/paper/2004.02015/) (2020)
- [Interpretation of NLP models through input marginalization](https://mlsanity.com/paper/2010.13984/) (2020)
- [Humans, AI, and Context: Understanding End-Users' Trust in a Real-World Computer Vision Application](https://mlsanity.com/paper/2305.08598/) (2023)

## Built on by (most cited first, 9 of 9)

- [LLMs for Explainable AI: A Comprehensive Survey](https://mlsanity.com/paper/2504.00125/) (2025)
- [Which Contributions Deserve Credit? Perceptions of Attribution in Human-AI Co-Creation](https://mlsanity.com/paper/2502.18357/) (2025)
- [From Text to Trust: Empowering AI-assisted Decision Making with Adaptive LLM-powered Analysis](https://mlsanity.com/paper/2502.11919/) (2025)
- [A Survey of Calibration Process for Black-Box LLMs](https://mlsanity.com/paper/2412.12767/) (2024)
- [Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Models](https://mlsanity.com/paper/2508.15396/) (2025)
- [Knowledge Augmented Complex Problem Solving with Large Language Models: A Survey](https://mlsanity.com/paper/2505.03418/) (2025)
- [FACTS&EVIDENCE: An Interactive Tool for Transparent Fine-Grained Factual Verification of Machine-Generated Text](https://mlsanity.com/paper/2503.14797/) (2025)
- [Hide or Highlight: Understanding the Impact of Factuality Expression on User Trust](https://mlsanity.com/paper/2508.07095/) (2025)
- [Signals of AI Hallucination: Designing Hallucination-Aware Cues for Embodied Conversational Agents in VR](https://mlsanity.com/paper/2609.28812/) (2026)

## Abstract (arXiv)

While humans increasingly rely on large language models (LLMs), they are susceptible to generating inaccurate or false information, also known as "hallucinations". Technical advancements have been made in algorithms that detect hallucinated content by assessing the factuality of the model's responses and attributing sections of those responses to specific source documents. However, there is limited research on how to effectively communicate this information to users in ways that will help them appropriately calibrate their trust toward LLMs. To address this issue, we conducted a scenario-based study (N=104) to systematically compare the impact of various design strategies for communicating factuality and source attribution on participants' ratings of trust, preferences, and ease in validating response accuracy. Our findings reveal that participants preferred a design in which phrases within a response were color-coded based on the computed factuality scores. Additionally, participants increased their trust ratings when relevant sections of the source material were highlighted or responses were annotated with reference numbers corresponding to those sources, compared to when they received no annotation in the source material. Our study offers practical design guidelines to facilitate human-LLM collaboration and it promotes a new human role to carefully evaluate and take responsibility for their use of LLM outputs.