# Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis

arXiv: https://arxiv.org/abs/2205.03784 · HTML: https://mlsanity.com/paper/2205.03784/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 47 references that are in the map.
- First posted on arXiv 8 May 2022.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Unbiased Scene Graph Generation from Biased Training](https://mlsanity.com/paper/2002.11949/) (2020)
- [LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention](https://mlsanity.com/paper/2010.01057/) (2020)
- [K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters](https://mlsanity.com/paper/2002.01808/) (2020)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction](https://mlsanity.com/paper/2104.07650/) (2021)
- [Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification](https://mlsanity.com/paper/2001.01536/) (2020)
- [Graph Convolution over Pruned Dependency Trees Improves Relation Extraction](https://mlsanity.com/paper/1809.10185/) (2018)
- [TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task](https://mlsanity.com/paper/2004.14855/) (2020)
- [An Improved Baseline for Sentence-level Relation Extraction](https://mlsanity.com/paper/2102.01373/) (2021)
- [Learning from Context or Names? An Empirical Study on Neural Relation Extraction](https://mlsanity.com/paper/2010.01923/) (2020)
- [Re-TACRED: Addressing Shortcomings of the TACRED Dataset](https://mlsanity.com/paper/2104.08398/) (2021)
- [SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations Between Pairs of Nominals](https://mlsanity.com/paper/1911.10422/) (2019)
- [Relation Classification with Entity Type Restriction](https://mlsanity.com/paper/2105.08393/) (2021)
- [Uncovering Main Causalities for Long-tailed Information Extraction](https://mlsanity.com/paper/2109.05213/) (2021)
- [Influence of Resampling on Accuracy of Imbalanced Classification](https://mlsanity.com/paper/1707.03905/) (2017)
- [CUSBoost: Cluster-based Under-sampling with Boosting for Imbalanced Classification](https://mlsanity.com/paper/1712.04356/) (2017)

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

- [Context-faithful Prompting for Large Language Models](https://mlsanity.com/paper/2303.11315/) (2023)
- [Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models](https://mlsanity.com/paper/2410.03659/) (2024)
- [Primacy Effect of ChatGPT](https://mlsanity.com/paper/2310.13206/) (2023)
- [Context versus Prior Knowledge in Language Models](https://mlsanity.com/paper/2404.04633/) (2024)
- [A Causal View of Entity Bias in (Large) Language Models](https://mlsanity.com/paper/2305.14695/) (2023)
- [Prompting Fairness: Integrating Causality to Debias Large Language Models](https://mlsanity.com/paper/2403.08743/) (2024)
- [SLANG: New Concept Comprehension of Large Language Models](https://mlsanity.com/paper/2401.12585/) (2024)
- [Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing](https://mlsanity.com/paper/2205.12640/) (2022)
- [Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extraction](https://mlsanity.com/paper/2210.04992/) (2022)
- [Getting Sick After Seeing a Doctor? Diagnosing and Mitigating Knowledge Conflicts in Event Temporal Reasoning](https://mlsanity.com/paper/2305.14970/) (2023)
- [Take Care of Your Prompt Bias! Investigating and Mitigating Prompt Bias in Factual Knowledge Extraction](https://mlsanity.com/paper/2403.09963/) (2024)
- [Assessing LLMs for Zero-shot Abstractive Summarization Through the Lens of Relevance Paraphrasing](https://mlsanity.com/paper/2406.03993/) (2024)
- [Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style](https://mlsanity.com/paper/2409.10955/) (2024)
- [Robust Natural Language Understanding with Residual Attention Debiasing](https://mlsanity.com/paper/2305.17627/) (2023)
- [Shortcut Learning in In-Context Learning: A Survey](https://mlsanity.com/paper/2411.02018/) (2024)
- [Uncovering Political Bias in Large Language Models using Parliamentary Voting Records](https://mlsanity.com/paper/2601.08785/) (2026)
- [Think Rationally about What You See: Continuous Rationale Extraction for Relation Extraction](https://mlsanity.com/paper/2305.03503/) (2023)
- [How Fragile is Relation Extraction under Entity Replacements?](https://mlsanity.com/paper/2305.13551/) (2023)
- [Taxonomy of Abstractive Dialogue Summarization: Scenarios, Approaches and Future Directions](https://mlsanity.com/paper/2210.09894/) (2022)
- [Learning from Semi-Factuals: A Debiased and Semantic-Aware Framework for Generalized Relation Discovery](https://mlsanity.com/paper/2401.06327/) (2024)
- [Consistent Document-Level Relation Extraction via Counterfactuals](https://mlsanity.com/paper/2407.06699/) (2024)
- [Mitigating Coordinate Prediction Bias from Positional Encoding Failures](https://mlsanity.com/paper/2510.22102/) (2025)
- [Reducing Sensitivity on Speaker Names for Text Generation from Dialogues](https://mlsanity.com/paper/2305.13833/) (2023)
- [Preconditioned Visual Language Inference with Weak Supervision](https://mlsanity.com/paper/2306.01753/) (2023)
- [Entity or Relation Embeddings? An Analysis of Encoding Strategies for Relation Extraction](https://mlsanity.com/paper/2312.11062/) (2023)
- [MixRED: A Mix-lingual Relation Extraction Dataset](https://mlsanity.com/paper/2403.15696/) (2024)
- [READ: Improving Relation Extraction from an ADversarial Perspective](https://mlsanity.com/paper/2404.02931/) (2024)
- [Explicit Inductive Inference using Large Language Models](https://mlsanity.com/paper/2408.14467/) (2024)
- [Few-shot Open Relation Extraction with Gaussian Prototype and Adaptive Margin](https://mlsanity.com/paper/2410.20320/) (2024)
- [A Variational Approach for Mitigating Entity Bias in Relation Extraction](https://mlsanity.com/paper/2506.11381/) (2025)

## Abstract (arXiv)

Recent literature focuses on utilizing the entity information in the sentence-level relation extraction (RE), but this risks leaking superficial and spurious clues of relations. As a result, RE still suffers from unintended entity bias, i.e., the spurious correlation between entity mentions (names) and relations. Entity bias can mislead the RE models to extract the relations that do not exist in the text. To combat this issue, some previous work masks the entity mentions to prevent the RE models from overfitting entity mentions. However, this strategy degrades the RE performance because it loses the semantic information of entities. In this paper, we propose the CORE (Counterfactual Analysis based Relation Extraction) debiasing method that guides the RE models to focus on the main effects of textual context without losing the entity information. We first construct a causal graph for RE, which models the dependencies between variables in RE models. Then, we propose to conduct counterfactual analysis on our causal graph to distill and mitigate the entity bias, that captures the causal effects of specific entity mentions in each instance. Note that our CORE method is model-agnostic to debias existing RE systems during inference without changing their training processes. Extensive experimental results demonstrate that our CORE yields significant gains on both effectiveness and generalization for RE. The source code is provided at: https://github.com/vanoracai/CoRE.