# A Closer Look at Claim Decomposition

arXiv: https://arxiv.org/abs/2403.11903 · HTML: https://mlsanity.com/paper/2403.11903/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 47 references that are in the map.
- First posted on arXiv 18 Mar 2024.

## Builds on (most cited first, 25 of 25)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [Asking and Answering Questions to Evaluate the Factual Consistency of Summaries](https://mlsanity.com/paper/2004.04228/) (2020)
- [FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization](https://mlsanity.com/paper/2005.03754/) (2020)
- [Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics](https://mlsanity.com/paper/2104.13346/) (2021)
- [QuestEval: Summarization Asks for Fact-based Evaluation](https://mlsanity.com/paper/2103.12693/) (2021)
- [QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization](https://mlsanity.com/paper/2112.08542/) (2021)
- [Fine-grained Hallucination Detection and Editing for Language Models](https://mlsanity.com/paper/2401.06855/) (2024)
- [Language Models with Conformal Factuality Guarantees](https://mlsanity.com/paper/2402.10978/) (2024)
- [Evaluating Factuality in Generation with Dependency-level Entailment](https://mlsanity.com/paper/2010.05478/) (2020)
- [WiCE: Real-World Entailment for Claims in Wikipedia](https://mlsanity.com/paper/2303.01432/) (2023)
- [Complex Claim Verification with Evidence Retrieved in the Wild](https://mlsanity.com/paper/2305.11859/) (2023)
- [Assessing The Factual Accuracy of Generated Text](https://mlsanity.com/paper/1905.13322/) (2019)
- [Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing](https://mlsanity.com/paper/2101.03289/) (2021)
- [Generating Literal and Implied Subquestions to Fact-check Complex Claims](https://mlsanity.com/paper/2205.06938/) (2022)
- [AmbiFC: Fact-Checking Ambiguous Claims with Evidence](https://mlsanity.com/paper/2104.00640/) (2021)
- [PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognition](https://mlsanity.com/paper/2212.10750/) (2022)
- [Summary-Source Proposition-level Alignment: Task, Datasets and Supervised Baseline](https://mlsanity.com/paper/2009.00590/) (2020)
- [Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations](https://mlsanity.com/paper/2311.04335/) (2023)
- [Logical Reasoning with Span-Level Predictions for Interpretable and Robust NLI Models](https://mlsanity.com/paper/2205.11432/) (2022)
- [Atomic Inference for NLI with Generated Facts as Atoms](https://mlsanity.com/paper/2305.13214/) (2023)

## Built on by (most cited first, 30 of 41)

- [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)
- [Decomposition Dilemmas: Does Claim Decomposition Boost or Burden Fact-Checking Performance?](https://mlsanity.com/paper/2411.02400/) (2024)
- [DnDScore: Decontextualization and Decomposition for Factuality Verification in Long-Form Text Generation](https://mlsanity.com/paper/2412.13175/) (2024)
- [Conformal Linguistic Calibration: Trading-off between Factuality and Specificity](https://mlsanity.com/paper/2502.19110/) (2025)
- [Towards Effective Extraction and Evaluation of Factual Claims](https://mlsanity.com/paper/2502.10855/) (2025)
- [From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization](https://mlsanity.com/paper/2410.13961/) (2024)
- [Core: Robust Factual Precision with Informative Sub-Claim Identification](https://mlsanity.com/paper/2407.03572/) (2024)
- [Localizing Factual Inconsistencies in Attributable Text Generation](https://mlsanity.com/paper/2410.07473/) (2024)
- [WikiVideo: Article Generation from Multiple Videos](https://mlsanity.com/paper/2504.00939/) (2025)
- [NLI under the Microscope: What Atomic Hypothesis Decomposition Reveals](https://mlsanity.com/paper/2502.08080/) (2025)
- [Optimizing Decomposition for Optimal Claim Verification](https://mlsanity.com/paper/2503.15354/) (2025)
- [VeriFastScore: Speeding up long-form factuality evaluation](https://mlsanity.com/paper/2505.16973/) (2025)
- [A New HOPE: Domain-agnostic Automatic Evaluation of Text Chunking](https://mlsanity.com/paper/2505.02171/) (2025)
- [Scalable and Domain-General Abstractive Proposition Segmentation](https://mlsanity.com/paper/2406.19803/) (2024)
- [All Claims Are Equal, but Some Claims Are More Equal Than Others: Importance-Sensitive Factuality Evaluation of LLM Generations](https://mlsanity.com/paper/2510.07083/) (2025)
- [FactEHR: A Dataset for Evaluating Factuality in Clinical Notes Using LLMs](https://mlsanity.com/paper/2412.12422/) (2024)
- [MedScore: Generalizable Factuality Evaluation of Free-Form Medical Answers by Domain-adapted Claim Decomposition and Verification](https://mlsanity.com/paper/2505.18452/) (2025)
- [Coordinating Search-Informed Reasoning and Reasoning-Guided Search in Claim Verification](https://mlsanity.com/paper/2506.07528/) (2025)
- [Beyond Precision: Importance-Aware Recall for Factuality Evaluation in Long-Form LLM Generation](https://mlsanity.com/paper/2604.03141/) (2026)
- [A Claim Decomposition Benchmark for Long-form Answer Verification](https://mlsanity.com/paper/2410.12558/) (2024)
- [Decide less, communicate more: On the construct validity of end-to-end fact-checking in medicine](https://mlsanity.com/paper/2506.20876/) (2025)
- [T-FIX: Text-Based Explanations with Features Interpretable to eXperts](https://mlsanity.com/paper/2511.04070/) (2025)
- [Distill and Align Decomposition for Enhanced Claim Verification](https://mlsanity.com/paper/2602.21857/) (2026)
- [Attributable by Construction: Claim-Anchored Provenance for Multi-Document Summarization](https://mlsanity.com/paper/2606.23989/) (2026)
- [Bonsai: Interpretable Tree-Adaptive Grounded Reasoning](https://mlsanity.com/paper/2504.03640/) (2025)
- [Seeing Through the MiRAGE: Evaluating Multimodal Retrieval Augmented Generation](https://mlsanity.com/paper/2510.24870/) (2025)
- [AGRaME: Any-Granularity Ranking with Multi-Vector Embeddings](https://mlsanity.com/paper/2405.15028/) (2024)
- [Cross-Document Event-Keyed Summarization](https://mlsanity.com/paper/2410.14795/) (2024)
- [How Grounded is Wikipedia? A Study on Structured Evidential Support and Retrieval](https://mlsanity.com/paper/2506.12637/) (2025)

## Abstract (arXiv)

As generated text becomes more commonplace, it is increasingly important to evaluate how well-supported such text is by external knowledge sources. Many approaches for evaluating textual support rely on some method for decomposing text into its individual subclaims which are scored against a trusted reference. We investigate how various methods of claim decomposition -- especially LLM-based methods -- affect the result of an evaluation approach such as the recently proposed FActScore, finding that it is sensitive to the decomposition method used. This sensitivity arises because such metrics attribute overall textual support to the model that generated the text even though error can also come from the metric's decomposition step. To measure decomposition quality, we introduce an adaptation of FActScore, which we call DecompScore. We then propose an LLM-based approach to generating decompositions inspired by Bertrand Russell's theory of logical atomism and neo-Davidsonian semantics and demonstrate its improved decomposition quality over previous methods.