mlsanityData to 7 Oct 2026

Influence of External Information on Large Language Models Mirrors Social Cognitive Patterns

arXiv 2305.04812 ↗First posted 8 May 2023cs.CLcited by 16

Not on the map. Why?

Abstract (arXiv)

Social cognitive theory explains how people learn and acquire knowledge through observing others. Recent years have witnessed the rapid development of large language models (LLMs), which suggests their potential significance as agents in the society. LLMs, as AI agents, can observe external information, which shapes their cognition and behaviors. However, the extent to which external information influences LLMs' cognition and behaviors remains unclear. This study investigates how external statements and opinions influence LLMs' thoughts and behaviors from a social cognitive perspective. Three experiments were conducted to explore the effects of external information on LLMs' memories, opinions, and social media behavioral decisions. Sociocognitive factors, including source authority, social identity, and social role, were analyzed to investigate their moderating effects. Results showed that external information can significantly shape LLMs' memories, opinions, and behaviors, with these changes mirroring human social cognitive patterns such as authority bias, in-group bias, emotional positivity, and emotion contagion. This underscores the challenges in developing safe and unbiased LLMs, and emphasizes the importance of understanding the susceptibility of LLMs to external influences.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 23 of its 87 references that are in the map. First posted on arXiv 8 May 2023.

Builds on

23 of 87 references.

References · 23

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  5. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  6. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  7. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  8. 2021Probing Classifiers: Promises, Shortcomings, and Advancescited by 831
  9. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  10. 2023Whose Opinions Do Language Models Reflect?cited by 759
  11. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 737
  12. 2019Defending Against Neural Fake Newscited by 553
11 more
  1. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 506
  2. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 351
  3. 2022Data Contamination: From Memorization to Exploitationcited by 234
  4. 2023On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspectivecited by 208
  5. 2021Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Docited by 178
  6. 2023Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuningcited by 171
  7. 2023Co-Writing with Opinionated Language Models Affects Users' Viewscited by 145
  8. 2021Towards artificial general intelligence via a multimodal foundation modelcited by 112
  9. 2021Evaluating the Robustness of Neural Language Models to Input Perturbationscited by 87
  10. 2017The spread of low-credibility content by social botscited by 73
  11. 2014Human language reveals a universal positivity biascited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 8; 2026: 2.

16 papers.

Sort:

By area:

  1. 2024Large Language Models and Games: A Survey and Roadmapcited by 91
  2. 2024Embodied LLM Agents Learn to Cooperate in Organized Teamscited by 81
  3. 2024Cognitive Biases in Large Language Models: A Survey and Mitigation Experimentscited by 20
  4. 2025Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Datacited by 10
  5. 2024The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Modelscited by 9
  6. 2025TH-Bench: Evaluating Evading Attacks via Humanizing AI Text on Machine-Generated Text Detectorscited by 8
  7. 2024MONAL: Model Autophagy Analysis for Modeling Human-AI Interactionscited by 7
  8. 2026ICON: Intent-Context Coupling for Efficient Multi-Turn Jailbreak Attackcited by 5
  9. 2025Paper Summary Attack: Jailbreaking LLMs through LLM Safety Paperscited by 3
  10. 2025Balancing Content Size in RAG-Text2SQL Systemcited by 2
  11. 2025SimKey: A Semantically Aware Key Module for Watermarking Language Modelscited by 2
  12. 2025Social Simulations with Large Language Model Risk Utopian Illusioncited by 2
4 more
  1. 2025Efficient Federated Search for Retrieval-Augmented Generation using Lightweight Routingcited by 1
  2. 2025HLPD: Aligning LLMs to Human Language Preference for Machine-Revised Text Detectioncited by 1
  3. 2024R^3AG: First Workshop on Refined and Reliable Retrieval Augmented Generationcited by 0
  4. 2026Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detectioncited by 0