# Atomic Inference for NLI with Generated Facts as Atoms

arXiv: https://arxiv.org/abs/2305.13214 · HTML: https://mlsanity.com/paper/2305.13214/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 22 May 2023.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization](https://mlsanity.com/paper/2111.09525/) (2021)
- [Towards Faithful Model Explanation in NLP: A Survey](https://mlsanity.com/paper/2209.11326/) (2022)
- [Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing](https://mlsanity.com/paper/2102.12060/) (2021)
- [WiCE: Real-World Entailment for Claims in Wikipedia](https://mlsanity.com/paper/2303.01432/) (2023)
- [ProoFVer: Natural Logic Theorem Proving for Fact Verification](https://mlsanity.com/paper/2108.11357/) (2021)
- [Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusters](https://mlsanity.com/paper/2204.07447/) (2022)
- [Finding a Balanced Degree of Automation for Summary Evaluation](https://mlsanity.com/paper/2109.11503/) (2021)
- [PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognition](https://mlsanity.com/paper/2212.10750/) (2022)
- [Natural Language Inference in Context -- Investigating Contextual Reasoning over Long Texts](https://mlsanity.com/paper/2011.04864/) (2020)
- [Logical Reasoning with Span-Level Predictions for Interpretable and Robust NLI Models](https://mlsanity.com/paper/2205.11432/) (2022)
- [Revisiting text decomposition methods for NLI-based factuality scoring of summaries](https://mlsanity.com/paper/2211.16853/) (2022)
- [Zero-shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens](https://mlsanity.com/paper/1805.02214/) (2018)
- [Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic](https://mlsanity.com/paper/2109.08927/) (2021)
- [Zero-shot Sequence Labeling for Transformer-based Sentence Classifiers](https://mlsanity.com/paper/2103.14465/) (2021)
- [Seeing Both the Forest and the Trees: Multi-head Attention for Joint Classification on Different Compositional Levels](https://mlsanity.com/paper/2011.00470/) (2020)

## Built on by (most cited first, 18 of 18)

- [A Closer Look at Claim Decomposition](https://mlsanity.com/paper/2403.11903/) (2024)
- [On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs](https://mlsanity.com/paper/2407.19200/) (2024)
- [InfoLossQA: Characterizing and Recovering Information Loss in Text Simplification](https://mlsanity.com/paper/2401.16475/) (2024)
- [Behavioral Analysis of Information Salience in Large Language Models](https://mlsanity.com/paper/2502.14613/) (2025)
- [Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics](https://mlsanity.com/paper/2505.18658/) (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)
- [QA-NatVer: Question Answering for Natural Logic-based Fact Verification](https://mlsanity.com/paper/2310.14198/) (2023)
- [AskQE: Question Answering as Automatic Evaluation for Machine Translation](https://mlsanity.com/paper/2504.11582/) (2025)
- [Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data Selection](https://mlsanity.com/paper/2505.20209/) (2025)
- [uMedSum: A Unified Framework for Advancing Medical Abstractive Summarization](https://mlsanity.com/paper/2408.12095/) (2024)
- [Extractive Fact Decomposition for Interpretable Natural Language Inference in one Forward Pass](https://mlsanity.com/paper/2509.18901/) (2025)
- [Atomic-SNLI: Fine-Grained Natural Language Inference through Atomic Fact Decomposition](https://mlsanity.com/paper/2601.06528/) (2026)
- [LLM-based Atomic Propositions help weak extractors: Evaluation of a Propositioner for triplet extraction](https://mlsanity.com/paper/2604.02866/) (2026)
- [A Hypothesis-Driven Framework for the Analysis of Self-Rationalising Models](https://mlsanity.com/paper/2402.04787/) (2024)
- [AEScorer: An Agentic Evidence-Grounded Framework for Graded Factuality Verification](https://mlsanity.com/paper/2601.03605/) (2026)
- [Atomic Visual Entailment: Enhancing Zero-Shot Vision-Language Reasoning through Atomic Fact Decomposition and Learned Selection](https://mlsanity.com/paper/2610.05630/) (2026)
- [Learning Proposition-Level Links from Sentence-Level Supervision for Neuro-Symbolic NLI](https://mlsanity.com/paper/2610.15158/) (2026)

## Abstract (arXiv)

With recent advances, neural models can achieve human-level performance on various natural language tasks. However, there are no guarantees that any explanations from these models are faithful, i.e. that they reflect the inner workings of the model. Atomic inference overcomes this issue, providing interpretable and faithful model decisions. This approach involves making predictions for different components (or atoms) of an instance, before using interpretable and deterministic rules to derive the overall prediction based on the individual atom-level predictions. We investigate the effectiveness of using LLM-generated facts as atoms, decomposing Natural Language Inference premises into lists of facts. While directly using generated facts in atomic inference systems can result in worse performance, with 1) a multi-stage fact generation process, and 2) a training regime that incorporates the facts, our fact-based method outperforms other approaches.