mlsanityData to 14 Oct 2026

Primacy Effect of ChatGPT

arXiv 2310.13206 ↗First posted 20 Oct 2023cs.CL cs.AIcited by 27

Not on the map. Why?

Abstract (arXiv)

Instruction-tuned large language models (LLMs), such as ChatGPT, have led to promising zero-shot performance in discriminative natural language understanding (NLU) tasks. This involves querying the LLM using a prompt containing the question, and the candidate labels to choose from. The question-answering capabilities of ChatGPT arise from its pre-training on large amounts of human-written text, as well as its subsequent fine-tuning on human preferences, which motivates us to ask: Does ChatGPT also inherits humans' cognitive biases? In this paper, we study the primacy effect of ChatGPT: the tendency of selecting the labels at earlier positions as the answer. We have two main findings: i) ChatGPT's decision is sensitive to the order of labels in the prompt; ii) ChatGPT has a clearly higher chance to select the labels at earlier positions as the answer. We hope that our experiments and analyses provide additional insights into building more reliable ChatGPT-based solutions. We release the source code at https://github.com/wangywUST/PrimacyEffectGPT.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Builds on 29 of its 43 references that are in the map. First posted on arXiv 20 Oct 2023.

Builds on

29 of 43 references.

References · 29

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  5. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  6. 2022LaMDA: Language Models for Dialog Applicationscited by 1,220
  7. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,202
  8. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
  9. 2022Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Modelcited by 559
  10. 2020GoEmotions: A Dataset of Fine-Grained Emotionscited by 486
  11. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 433
  12. 2023ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPTcited by 250
17 more
  1. 2020Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classificationcited by 175
  2. 2023Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERTcited by 155
  3. 2022MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languagescited by 146
  4. 2023Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulnesscited by 130
  5. 2023Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!cited by 119
  6. 2020TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Taskcited by 96
  7. 2023Mitigating Label Biases for In-context Learningcited by 89
  8. 2021An Improved Baseline for Sentence-level Relation Extractioncited by 81
  9. 2022How would Stance Detection Techniques Evolve after the Launch of ChatGPT?cited by 76
  10. 2021Re-TACRED: Addressing Shortcomings of the TACRED Datasetcited by 74
  11. 2023Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluationcited by 69
  12. 2023Zero-shot Temporal Relation Extraction with ChatGPTcited by 53
  13. 2023On the Educational Impact of ChatGPT: Is Artificial Intelligence Ready to Obtain a University Degree?cited by 48
  14. 2023An Empirical Study on Information Extraction using Large Language Modelscited by 46
  15. 2022Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysiscited by 30
  16. 2023Applying BERT and ChatGPT for Sentiment Analysis of Lyme Disease in Scientific Literaturecited by 26
  17. 2023The moral authority of ChatGPTcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 10; 2025: 14; 2026: 3.

27 papers.

Sort:

By area:

  1. 2024Eliminating Position Bias of Language Models: A Mechanistic Approachcited by 65
  2. 2024Insights into LLM Long-Context Failures: When Transformers Know but Don't Tellcited by 36
  3. 2024Cognitive Biases in Large Language Models: A Survey and Mitigation Experimentscited by 20
  4. 2024Towards Hierarchical Multi-Agent Workflows for Zero-Shot Prompt Optimizationcited by 10
  5. 2025Positional Biases Shift as Inputs Approach Context Window Limitscited by 9
  6. 2024Self-Consistency Falls Short! The Adverse Effects of Positional Bias on Long-Context Problemscited by 7
  7. 2025Hidden in the Haystack: Smaller Needles are More Difficult for LLMs to Findcited by 7
  8. 2025Quantifying Cognitive Bias Induction in LLM-Generated Contentcited by 7
  9. 2025CaRT: Teaching LLM Agents to Know When They Know Enoughcited by 7
  10. 2024Vulnerability of LLMs to Vertically Aligned Text Manipulationscited by 6
  11. 2025Understanding the Anchoring Effect of LLM with Synthetic Data: Existence, Mechanism, and Potential Mitigationscited by 6
  12. 2025Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Modelscited by 6
15 more
  1. 2025Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Modelscited by 5
  2. 2025Fragile Preferences: A Deep Dive Into Order Effects in Large Language Modelscited by 5
  3. 2025Emergence of Episodic Memory in Transformers: Characterizing Changes in Temporal Structure of Attention Scores During Trainingcited by 4
  4. 2025Emergence of the Primacy Effect in Structured State-Space Modelscited by 4
  5. 2025Generalised Probabilistic Modelling and Improved Uncertainty Estimation in Comparative LLM-as-a-judgecited by 4
  6. 2024Image First or Text First? Optimising the Sequencing of Modalities in Large Language Model Prompting and Reasoning Taskscited by 3
  7. 2024The Computational Anatomy of Humility: Modeling Intellectual Humility in Online Public Discoursecited by 3
  8. 2024Order Matters! An Empirical Study on Large Language Models' Input Order Bias in Software Fault Localizationcited by 3
  9. 2025LLMs as In-Context Meta-Learners for Model and Hyperparameter Selectioncited by 3
  10. 2025AI Security Beyond Core Domains: Resume Screening as a Case Study of Adversarial Vulnerabilities in Specialized LLM Applicationscited by 3
  11. 2025Social Simulations with Large Language Model Risk Utopian Illusioncited by 2
  12. 2026Social Dynamics as Critical Vulnerabilities that Undermine Objective Decision-Making in LLM Collectivescited by 2
  13. 2026The yes-no bias of large language models reflects answer order and wording, not shifts in moral judgmentcited by 1
  14. 2024A Survey on the Real Power of ChatGPTcited by 0
  15. 2026Temporal Dependencies in In-Context Learning: The Role of Induction Headscited by 0