# Merging Facts, Crafting Fallacies: Evaluating the Contradictory Nature of Aggregated Factual Claims in Long-Form Generations

arXiv: https://arxiv.org/abs/2402.05629 · HTML: https://mlsanity.com/paper/2402.05629/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 8 Feb 2024.

## Builds on (most cited first, 26 of 26)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization](https://mlsanity.com/paper/2111.09525/) (2021)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [Evaluating Verifiability in Generative Search Engines](https://mlsanity.com/paper/2304.09848/) (2023)
- [Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics](https://mlsanity.com/paper/2104.13346/) (2021)
- [Measuring Attribution in Natural Language Generation Models](https://mlsanity.com/paper/2112.12870/) (2021)
- [ASQA: Factoid Questions Meet Long-Form Answers](https://mlsanity.com/paper/2204.06092/) (2022)
- [Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2](https://mlsanity.com/paper/2311.10702/) (2023)
- [A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation](https://mlsanity.com/paper/2104.08704/) (2021)
- [Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus](https://mlsanity.com/paper/2311.13230/) (2023)
- [LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization](https://mlsanity.com/paper/2301.13298/) (2023)
- [Joint Passage Ranking for Diverse Multi-Answer Retrieval](https://mlsanity.com/paper/2104.08445/) (2021)
- [Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization](https://mlsanity.com/paper/2209.03549/) (2022)
- [Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction](https://mlsanity.com/paper/2011.13137/) (2020)
- [Answering Open-Domain Multi-Answer Questions via a Recall-then-Verify Framework](https://mlsanity.com/paper/2110.08544/) (2021)

## Built on by (most cited first, 14 of 14)

- [VERISCORE: Evaluating the factuality of verifiable claims in long-form text generation](https://mlsanity.com/paper/2406.19276/) (2024)
- [Molecular Facts: Desiderata for Decontextualization in LLM Fact Verification](https://mlsanity.com/paper/2406.20079/) (2024)
- [Atomic Calibration of LLMs in Long-Form Generations](https://mlsanity.com/paper/2410.13246/) (2024)
- [Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback](https://mlsanity.com/paper/2501.10799/) (2025)
- [AmbigDocs: Reasoning across Documents on Different Entities under the Same Name](https://mlsanity.com/paper/2404.12447/) (2024)
- [FactAlign: Long-form Factuality Alignment of Large Language Models](https://mlsanity.com/paper/2410.01691/) (2024)
- [UNCLE: Benchmarking Uncertainty Expressions in Long-Form Generation](https://mlsanity.com/paper/2505.16922/) (2025)
- [Can LLMs Automate Fact-Checking Article Writing?](https://mlsanity.com/paper/2503.17684/) (2025)
- [Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization](https://mlsanity.com/paper/2502.19127/) (2025)
- [PASS-FC: Progressive and Adaptive Search Scheme for Fact Checking of Comprehensive Claims](https://mlsanity.com/paper/2504.09866/) (2025)
- [The Psychology of Falsehood: A Human-Centric Survey of Misinformation Detection](https://mlsanity.com/paper/2509.15896/) (2025)
- [Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research](https://mlsanity.com/paper/2604.17843/) (2026)
- [Culinary Class Wars: Evaluating LLMs using ASH in Cuisine Transfer Task](https://mlsanity.com/paper/2411.01996/) (2024)
- [Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation](https://mlsanity.com/paper/2607.09349/) (2026)

## Abstract (arXiv)

Long-form generations from large language models (LLMs) contain a mix of factual and non-factual claims, making evaluating factuality difficult. Prior works evaluate the factuality of a long paragraph by decomposing it into multiple facts, verifying those facts independently, and aggregating the results. Such methods assume that combining factual claims forms a factual paragraph. The above assumption can be violated: we show that strong open-source models like Llama-chat can generate paragraphs that contain verifiable facts, but the facts are combined into a non-factual paragraph due to entity ambiguity. We further reveal that existing factuality metrics, including FActScore and citation recall, cannot properly evaluate these non-factual paragraphs and overestimate their factuality. To address this, we introduce an enhanced metric, D-FActScore, specifically designed for content with ambiguous entities. We evaluate the D-FActScores of people biographies generated by retrieval-augmented LLMs. We show that D-FActScore can better assess the factuality of paragraphs with entity ambiguity than FActScore. We also find that four widely used open-source LLMs tend to mix information of distinct entities to form non-factual paragraphs, making their D-FActScore much lower than FActScore by over 10%.