# A Causal View of Entity Bias in (Large) Language Models

arXiv: https://arxiv.org/abs/2305.14695 · HTML: https://mlsanity.com/paper/2305.14695/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 51 references that are in the map.
- First posted on arXiv 24 May 2023.

## Builds on (most cited first, 30 of 39)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [Entity-Based Knowledge Conflicts in Question Answering](https://mlsanity.com/paper/2109.05052/) (2021)
- [RealTime QA: What's the Answer Right Now?](https://mlsanity.com/paper/2207.13332/) (2022)
- [Causal Intervention for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2009.12547/) (2020)
- [Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias](https://mlsanity.com/paper/2004.12265/) (2020)
- [Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond](https://mlsanity.com/paper/2109.00725/) (2021)
- [Large Language Models with Controllable Working Memory](https://mlsanity.com/paper/2211.05110/) (2022)
- [Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence](https://mlsanity.com/paper/2210.13701/) (2022)
- [Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models](https://mlsanity.com/paper/2106.06087/) (2021)
- [StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models](https://mlsanity.com/paper/2205.11388/) (2022)
- [Causal Intervention for Leveraging Popularity Bias in Recommendation](https://mlsanity.com/paper/2105.06067/) (2021)
- [Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System](https://mlsanity.com/paper/2010.15363/) (2020)
- [An Improved Baseline for Sentence-level Relation Extraction](https://mlsanity.com/paper/2102.01373/) (2021)
- [Context-faithful Prompting for Large Language Models](https://mlsanity.com/paper/2303.11315/) (2023)
- [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)
- [Towards Robustness Against Natural Language Word Substitutions](https://mlsanity.com/paper/2107.13541/) (2021)
- [Text and Causal Inference: A Review of Using Text to Remove Confounding from Causal Estimates](https://mlsanity.com/paper/2005.00649/) (2020)
- [Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting](https://mlsanity.com/paper/2004.14088/) (2020)
- [Generalizing to the Future: Mitigating Entity Bias in Fake News Detection](https://mlsanity.com/paper/2204.09484/) (2022)
- [Annotation Inconsistency and Entity Bias in MultiWOZ](https://mlsanity.com/paper/2105.14150/) (2021)

## Built on by (most cited first, 21 of 21)

- [Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models](https://mlsanity.com/paper/2410.07176/) (2024)
- [Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment](https://mlsanity.com/paper/2403.02738/) (2024)
- [Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models](https://mlsanity.com/paper/2410.03659/) (2024)
- [Controllable Context Sensitivity and the Knob Behind It](https://mlsanity.com/paper/2411.07404/) (2024)
- [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)
- [Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges](https://mlsanity.com/paper/2409.19993/) (2024)
- [Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure](https://mlsanity.com/paper/2602.08783/) (2026)
- [Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning](https://mlsanity.com/paper/2502.04667/) (2025)
- [Preference Learning for AI Alignment: a Causal Perspective](https://mlsanity.com/paper/2506.05967/) (2025)
- [Investigating Tool-Memory Conflicts in Tool-Augmented LLMs](https://mlsanity.com/paper/2601.09760/) (2026)
- [Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training](https://mlsanity.com/paper/2506.09433/) (2025)
- [Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation](https://mlsanity.com/paper/2409.12468/) (2024)
- [Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models](https://mlsanity.com/paper/2502.21123/) (2025)
- [Oreo: A Plug-in Context Reconstructor to Enhance Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.13019/) (2025)
- [Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution](https://mlsanity.com/paper/2605.02640/) (2026)
- [Pretraining Exposure Explains Popularity Judgments in Large Language Models](https://mlsanity.com/paper/2605.12382/) (2026)
- [Counterfactual Samples Constructing and Training for Commonsense Statements Estimation](https://mlsanity.com/paper/2412.20563/) (2024)
- [A Pluggable Multi-Task Learning Framework for Sentiment-Aware Financial Relation Extraction](https://mlsanity.com/paper/2506.12452/) (2025)
- [OR-VSKC: Resolving Visual-Semantic Knowledge Conflicts in Operating Rooms with Synthetic Data-Guided Alignment](https://mlsanity.com/paper/2506.22500/) (2025)
- [Epistemic Blinding: An Inference-Time Protocol for Auditing Prior Contamination in LLM-Assisted Analysis](https://mlsanity.com/paper/2604.06013/) (2026)

## Abstract (arXiv)

Entity bias widely affects pretrained (large) language models, causing them to rely on (biased) parametric knowledge to make unfaithful predictions. Although causality-inspired methods have shown great potential to mitigate entity bias, it is hard to precisely estimate the parameters of underlying causal models in practice. The rise of black-box LLMs also makes the situation even worse, because of their inaccessible parameters and uncalibrated logits. To address these problems, we propose a specific structured causal model (SCM) whose parameters are comparatively easier to estimate. Building upon this SCM, we propose causal intervention techniques to mitigate entity bias for both white-box and black-box settings. The proposed causal intervention perturbs the original entity with neighboring entities. This intervention reduces specific biasing information pertaining to the original entity while still preserving sufficient semantic information from similar entities. Under the white-box setting, our training-time intervention improves OOD performance of PLMs on relation extraction (RE) and machine reading comprehension (MRC) by 5.7 points and by 9.1 points, respectively. Under the black-box setting, our in-context intervention effectively reduces the entity-based knowledge conflicts of GPT-3.5, achieving up to 20.5 points of improvement of exact match accuracy on MRC and up to 17.6 points of reduction in memorization ratio on RE. Our code is available at https://github.com/luka-group/Causal-View-of-Entity-Bias.