# One vs. Many: Comprehending Accurate Information from Multiple Erroneous and Inconsistent AI Generations

arXiv: https://arxiv.org/abs/2405.05581 · HTML: https://mlsanity.com/paper/2405.05581/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 78 references that are in the map.
- First posted on arXiv 9 May 2024.

## Builds on (most cited first, 30 of 34)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://mlsanity.com/paper/2009.02252/) (2020)
- [SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization](https://mlsanity.com/paper/2111.09525/) (2021)
- [Asking and Answering Questions to Evaluate the Factual Consistency of Summaries](https://mlsanity.com/paper/2004.04228/) (2020)
- [Measuring and Improving Consistency in Pretrained Language Models](https://mlsanity.com/paper/2102.01017/) (2021)
- [Unsolved Problems in ML Safety](https://mlsanity.com/paper/2109.13916/) (2021)
- [Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making](https://mlsanity.com/paper/2001.02114/) (2020)
- [QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization](https://mlsanity.com/paper/2112.08542/) (2021)
- [Reducing conversational agents' overconfidence through linguistic calibration](https://mlsanity.com/paper/2012.14983/) (2020)
- [On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection](https://mlsanity.com/paper/1811.07901/) (2018)
- [LM vs LM: Detecting Factual Errors via Cross Examination](https://mlsanity.com/paper/2305.13281/) (2023)
- [Explaining Explanations in AI](https://mlsanity.com/paper/1811.01439/) (2018)
- [To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making](https://mlsanity.com/paper/2102.09692/) (2021)
- [Logic-Guided Data Augmentation and Regularization for Consistent Question Answering](https://mlsanity.com/paper/2004.10157/) (2020)
- [Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanations](https://mlsanity.com/paper/1910.03065/) (2019)
- [Explainable AI is Dead, Long Live Explainable AI! Hypothesis-driven decision support](https://mlsanity.com/paper/2302.12389/) (2023)
- [Do People Engage Cognitively with AI? Impact of AI Assistance on Incidental Learning](https://mlsanity.com/paper/2202.05402/) (2022)
- [Sensecape: Enabling Multilevel Exploration and Sensemaking with Large Language Models](https://mlsanity.com/paper/2305.11483/) (2023)
- [Conceptual Metaphors Impact Perceptions of Human-AI Collaboration](https://mlsanity.com/paper/2008.02311/) (2020)
- [Comparing Traditional and LLM-based Search for Consumer Choice: A Randomized Experiment](https://mlsanity.com/paper/2307.03744/) (2023)
- [Who Goes First? Influences of Human-AI Workflow on Decision Making in Clinical Imaging](https://mlsanity.com/paper/2205.09696/) (2022)
- [RELIC: Investigating Large Language Model Responses using Self-Consistency](https://mlsanity.com/paper/2311.16842/) (2023)
- [Toward General Design Principles for Generative AI Applications](https://mlsanity.com/paper/2301.05578/) (2023)

## Built on by (most cited first, 13 of 13)

- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistencies](https://mlsanity.com/paper/2502.08554/) (2025)
- [Prompt-Reverse Inconsistency: LLM Self-Inconsistency Beyond Generative Randomness and Prompt Paraphrasing](https://mlsanity.com/paper/2504.01282/) (2025)
- [Surfacing Variations to Calibrate Perceived Reliability of MLLM-generated Image Descriptions](https://mlsanity.com/paper/2507.15692/) (2025)
- [Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents](https://mlsanity.com/paper/2606.05391/) (2026)
- [Network-Level Prompt and Trait Leakage in Local Research Agents](https://mlsanity.com/paper/2508.20282/) (2025)
- [ClearFairy: Capturing Creative Workflows through Decision Structuring, In-Situ Questioning, and Rationale Inference](https://mlsanity.com/paper/2509.14537/) (2025)
- [Generative AI for Research Data Processing: Lessons Learnt From Three Use Cases](https://mlsanity.com/paper/2504.15829/) (2025)
- [Leveraging Approximate Caching for Faster Retrieval-Augmented Generation](https://mlsanity.com/paper/2503.05530/) (2025)
- [AI Ethics and Social Norms: Exploring ChatGPT's Capabilities From What to How](https://mlsanity.com/paper/2504.18044/) (2025)
- [InFerActive: Interactive Tree-Based Exploration of LLM Sampling for Safety Evaluation](https://mlsanity.com/paper/2512.10234/) (2025)
- [Wisdom Of The (AI) Crowd: Investigating Artificial Swarm Intelligence In Large Language Models](https://mlsanity.com/paper/2606.31404/) (2026)
- [Schema-Guided Hierarchical Information Extraction and Semantic Evaluation Using Generative AI](https://mlsanity.com/paper/2608.06167/) (2026)

## Abstract (arXiv)

As Large Language Models (LLMs) are nondeterministic, the same input can generate different outputs, some of which may be incorrect or hallucinated. If run again, the LLM may correct itself and produce the correct answer. Unfortunately, most LLM-powered systems resort to single results which, correct or not, users accept. Having the LLM produce multiple outputs may help identify disagreements or alternatives. However, it is not obvious how the user will interpret conflicts or inconsistencies. To this end, we investigate how users perceive the AI model and comprehend the generated information when they receive multiple, potentially inconsistent, outputs. Through a preliminary study, we identified five types of output inconsistencies. Based on these categories, we conducted a study (N=252) in which participants were given one or more LLM-generated passages to an information-seeking question. We found that inconsistency within multiple LLM-generated outputs lowered the participants' perceived AI capacity, while also increasing their comprehension of the given information. Specifically, we observed that this positive effect of inconsistencies was most significant for participants who read two passages, compared to those who read three. Based on these findings, we present design implications that, instead of regarding LLM output inconsistencies as a drawback, we can reveal the potential inconsistencies to transparently indicate the limitations of these models and promote critical LLM usage.