# Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference

arXiv: https://arxiv.org/abs/2211.11875 · HTML: https://mlsanity.com/paper/2211.11875/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 42 references that are in the map.
- First posted on arXiv 21 Nov 2022.

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

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization](https://mlsanity.com/paper/2111.09525/) (2021)
- [Measuring and Improving Consistency in Pretrained Language Models](https://mlsanity.com/paper/2102.01017/) (2021)
- [Differentiation of Blackbox Combinatorial Solvers](https://mlsanity.com/paper/1912.02175/) (2019)
- [Unsupervised Commonsense Question Answering with Self-Talk](https://mlsanity.com/paper/2004.05483/) (2020)
- [Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations](https://mlsanity.com/paper/2205.11822/) (2022)
- [Editable Neural Networks](https://mlsanity.com/paper/2004.00345/) (2020)
- [Synthetic QA Corpora Generation with Roundtrip Consistency](https://mlsanity.com/paper/1906.05416/) (2019)
- [Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation](https://mlsanity.com/paper/2010.10042/) (2020)
- [Dialogue Natural Language Inference](https://mlsanity.com/paper/1811.00671/) (2018)
- [Transforming Question Answering Datasets Into Natural Language Inference Datasets](https://mlsanity.com/paper/1809.02922/) (2018)
- [Logic-Guided Data Augmentation and Regularization for Consistent Question Answering](https://mlsanity.com/paper/2004.10157/) (2020)
- [A Logic-Driven Framework for Consistency of Neural Models](https://mlsanity.com/paper/1909.00126/) (2019)
- [BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief](https://mlsanity.com/paper/2109.14723/) (2021)
- [Evaluating Coherence in Dialogue Systems using Entailment](https://mlsanity.com/paper/1904.03371/) (2019)
- [Can NLI Models Verify QA Systems' Predictions?](https://mlsanity.com/paper/2104.08731/) (2021)
- [General-Purpose Question-Answering with Macaw](https://mlsanity.com/paper/2109.02593/) (2021)
- [Sunny and Dark Outside?! Improving Answer Consistency in VQA through Entailed Question Generation](https://mlsanity.com/paper/1909.04696/) (2019)
- [Generating Persona Consistent Dialogues by Exploiting Natural Language Inference](https://mlsanity.com/paper/1911.05889/) (2019)

## Built on by (most cited first, 30 of 40)

- [Conformal Language Modeling](https://mlsanity.com/paper/2306.10193/) (2023)
- [Empowering LLMs with Logical Reasoning: A Comprehensive Survey](https://mlsanity.com/paper/2502.15652/) (2025)
- [Internal Consistency and Self-Feedback in Large Language Models: A Survey](https://mlsanity.com/paper/2407.14507/) (2024)
- [Benchmarking and Improving Generator-Validator Consistency of Language Models](https://mlsanity.com/paper/2310.01846/) (2023)
- [The Consensus Game: Language Model Generation via Equilibrium Search](https://mlsanity.com/paper/2310.09139/) (2023)
- [Interactive Natural Language Processing](https://mlsanity.com/paper/2305.13246/) (2023)
- [Logically Consistent Language Models via Neuro-Symbolic Integration](https://mlsanity.com/paper/2409.13724/) (2024)
- [The Trickle-down Impact of Reward (In-)consistency on RLHF](https://mlsanity.com/paper/2309.16155/) (2023)
- [Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language](https://mlsanity.com/paper/2306.02797/) (2023)
- [A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation](https://mlsanity.com/paper/2406.06950/) (2024)
- [Language Models with Rationality](https://mlsanity.com/paper/2305.14250/) (2023)
- [Semantic Consistency for Assuring Reliability of Large Language Models](https://mlsanity.com/paper/2308.09138/) (2023)
- [Consistency in Language Models: Current Landscape, Challenges, and Future Directions](https://mlsanity.com/paper/2505.00268/) (2025)
- [Improving Consistency in Large Language Models through Chain of Guidance](https://mlsanity.com/paper/2502.15924/) (2025)
- [MMRAG: Multi-Mode Retrieval-Augmented Generation with Large Language Models for Biomedical In-Context Learning](https://mlsanity.com/paper/2502.15954/) (2025)
- [Improved Beam Search for Hallucination Mitigation in Abstractive Summarization](https://mlsanity.com/paper/2212.02712/) (2022)
- [Incentivizing Truthful Language Models via Peer Elicitation Games](https://mlsanity.com/paper/2505.13636/) (2025)
- [From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency](https://mlsanity.com/paper/2404.12145/) (2024)
- [Prompt to be Consistent is Better than Self-Consistent? Few-Shot and Zero-Shot Fact Verification with Pre-trained Language Models](https://mlsanity.com/paper/2306.02569/) (2023)
- [Beyond Calibration: Do a Typed-Decision Model's Probabilities Obey the Probability Axioms?](https://mlsanity.com/paper/2609.33209/) (2026)
- [Zero-shot Learning with Minimum Instruction to Extract Social Determinants and Family History from Clinical Notes using GPT Model](https://mlsanity.com/paper/2309.05475/) (2023)
- [Beyond the Singular: Revealing the Value of Multiple Generations in Benchmark Evaluation](https://mlsanity.com/paper/2502.08943/) (2025)
- [Where Knowledge Collides: A Mechanistic Study of Intra-Memory Knowledge Conflict in Language Models](https://mlsanity.com/paper/2601.09445/) (2026)
- [Pixels Don't Lie (But Your Detector Might): Bootstrapping MLLM-as-a-Judge for Trustworthy Deepfake Detection and Reasoning Supervision](https://mlsanity.com/paper/2602.19715/) (2026)
- [KNOW How to Make Up Your Mind! Adversarially Detecting and Alleviating Inconsistencies in Natural Language Explanations](https://mlsanity.com/paper/2306.02980/) (2023)
- [No Strong Feelings One Way or Another: Re-operationalizing Neutrality in Natural Language Inference](https://mlsanity.com/paper/2306.09918/) (2023)
- [VideoJudge: Bootstrapping Enables Scalable Supervision of MLLM-as-a-Judge for Video Understanding](https://mlsanity.com/paper/2509.21451/) (2025)
- [Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning](https://mlsanity.com/paper/2604.01170/) (2026)
- [Dutch Books for Language Models](https://mlsanity.com/paper/2609.02797/) (2026)
- [Improving Consistency in Retrieval-Augmented Systems with Group Similarity Rewards](https://mlsanity.com/paper/2510.04392/) (2025)

## Abstract (arXiv)

While large pre-trained language models are powerful, their predictions often lack logical consistency across test inputs. For example, a state-of-the-art Macaw question-answering (QA) model answers 'Yes' to 'Is a sparrow a bird?' and 'Does a bird have feet?' but answers 'No' to 'Does a sparrow have feet?'. To address this failure mode, we propose a framework, Consistency Correction through Relation Detection, or ConCoRD, for boosting the consistency and accuracy of pre-trained NLP models using pre-trained natural language inference (NLI) models without fine-tuning or re-training. Given a batch of test inputs, ConCoRD samples several candidate outputs for each input and instantiates a factor graph that accounts for both the model's belief about the likelihood of each answer choice in isolation and the NLI model's beliefs about pair-wise answer choice compatibility. We show that a weighted MaxSAT solver can efficiently compute high-quality answer choices under this factor graph, improving over the raw model's predictions. Our experiments demonstrate that ConCoRD consistently boosts accuracy and consistency of off-the-shelf closed-book QA and VQA models using off-the-shelf NLI models, notably increasing accuracy of LXMERT on ConVQA by 5% absolute. See https://ericmitchell.ai/emnlp-2022-concord/ for code and data.