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

arXiv: https://arxiv.org/abs/2305.04812 · HTML: https://mlsanity.com/paper/2305.04812/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 87 references that are in the map.
- First posted on arXiv 8 May 2023.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Defending Against Neural Fake News](https://mlsanity.com/paper/1905.12616/) (2019)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback](https://mlsanity.com/paper/2302.12813/) (2023)
- [Data Contamination: From Memorization to Exploitation](https://mlsanity.com/paper/2203.08242/) (2022)
- [On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective](https://mlsanity.com/paper/2302.12095/) (2023)
- [Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do](https://mlsanity.com/paper/2103.11790/) (2021)
- [Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2303.15647/) (2023)
- [Co-Writing with Opinionated Language Models Affects Users' Views](https://mlsanity.com/paper/2302.00560/) (2023)
- [Towards artificial general intelligence via a multimodal foundation model](https://mlsanity.com/paper/2110.14378/) (2021)
- [Evaluating the Robustness of Neural Language Models to Input Perturbations](https://mlsanity.com/paper/2108.12237/) (2021)
- [The spread of low-credibility content by social bots](https://mlsanity.com/paper/1707.07592/) (2017)
- [Human language reveals a universal positivity bias](https://mlsanity.com/paper/1406.3855/) (2014)

## Built on by (most cited first, 16 of 16)

- [Large Language Models and Games: A Survey and Roadmap](https://mlsanity.com/paper/2402.18659/) (2024)
- [Embodied LLM Agents Learn to Cooperate in Organized Teams](https://mlsanity.com/paper/2403.12482/) (2024)
- [Cognitive Biases in Large Language Models: A Survey and Mitigation Experiments](https://mlsanity.com/paper/2412.00323/) (2024)
- [The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models](https://mlsanity.com/paper/2411.11407/) (2024)
- [Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data](https://mlsanity.com/paper/2503.05587/) (2025)
- [TH-Bench: Evaluating Evading Attacks via Humanizing AI Text on Machine-Generated Text Detectors](https://mlsanity.com/paper/2503.08708/) (2025)
- [MONAL: Model Autophagy Analysis for Modeling Human-AI Interactions](https://mlsanity.com/paper/2402.11271/) (2024)
- [ICON: Intent-Context Coupling for Efficient Multi-Turn Jailbreak Attack](https://mlsanity.com/paper/2601.20903/) (2026)
- [Paper Summary Attack: Jailbreaking LLMs through LLM Safety Papers](https://mlsanity.com/paper/2507.13474/) (2025)
- [Balancing Content Size in RAG-Text2SQL System](https://mlsanity.com/paper/2502.15723/) (2025)
- [SimKey: A Semantically Aware Key Module for Watermarking Language Models](https://mlsanity.com/paper/2510.12828/) (2025)
- [Social Simulations with Large Language Model Risk Utopian Illusion](https://mlsanity.com/paper/2510.21180/) (2025)
- [Efficient Federated Search for Retrieval-Augmented Generation using Lightweight Routing](https://mlsanity.com/paper/2502.19280/) (2025)
- [HLPD: Aligning LLMs to Human Language Preference for Machine-Revised Text Detection](https://mlsanity.com/paper/2511.06942/) (2025)
- [R^3AG: First Workshop on Refined and Reliable Retrieval Augmented Generation](https://mlsanity.com/paper/2410.20598/) (2024)
- [Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection](https://mlsanity.com/paper/2606.30587/) (2026)

## 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.