EMNLP Findings2024
Will LLMs Sink or Swim? Exploring Decision-Making Under Pressure
Kyusik Kim, Hyeonseok Jeon, Jeongwoo Ryu, Bongwon Suh
Abstract
Recent advancements in Large Language Models (LLMs) have demonstrated their ability to simulate human-like decision-making, yet the impact of psychological pressures on their decision-making processes remains underexplored. To understand how psychological pressures influence decision-making in LLMs, we tested LLMs on various high-level tasks, using both explicit and implicit pressure prompts. Moreover, we examined LLM responses under different personas to compare with human behavior under pressure. Our findings show that pressures significantly affect LLMs' decision-making, varying across tasks and models. Persona-based analysis suggests some models exhibit human-like sensitivity to pressure, though with some variability. Furthermore, by analyzing both the responses and reasoning patterns, we identified the values LLMs prioritize under specific social pressures. These insights deepen our understanding of LLM behavior and demonstrate the potential for more realistic social simulation experiments. Caution: This paper includes offensive words that could potentially cause unpleasantness.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Training Socially Aligned Language Models on Simulated Social Interactions cites Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies
- Can Large Language Model Agents Simulate Human Trust Behavior? cites Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysis
- Can Large Language Model Agents Simulate Human Trust Behavior? cites Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies
Builds on9
- Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject StudiesGati V. Aher, Rosa I. Arriaga, Adam Tauman KalaiICML 2023 · 651 citations
- Can Large Language Model Agents Simulate Human Trust Behavior?Chengxing Xie, Canyu Chen, Feiran Jia, Ziyu Ye et al.NeurIPS 2024 · 183 citations
- Can Large Language Models Serve as Rational Players in Game Theory? A Systematic AnalysisCaoyun Fan, Jindou Chen, Yaohui Jin, Hao HeAAAI 2024 · 123 citations
- Training Socially Aligned Language Models on Simulated Social InteractionsRuibo Liu, Ruixin Yang, Chenyan Jia, Ge Zhang et al.ICLR 2024 · 97 citations
- Empathy Is All You Need: How a Conversational Agent Should Respond to Verbal AbuseHyojin Chin, Lebogang Wame Molefi, Mun Yong YiCHI 2020 · 89 citations
Related papers
- Modeling Human Subjectivity in LLMs Using Explicit and Implicit Human Factors in PersonasSalvatore Giorgi, Tingting Liu, Ankit Aich, Kelsey Isman et al.EMNLP Findings 2024 · 4 citations
- StressPrompt: Does Stress Impact Large Language Models and Human Performance Similarly?Guobin Shen, Dongcheng Zhao, Aorigele Bao, Xiang He et al.AAAI 2025 · 9 citations
- Do LLM Agents Mirror Socio-Cognitive Effects in Power-Asymmetric Conversations?Anvesh Rao Vijjini, Sagar Manjunath, Snigdha ChaturvediACL 2026
- Inertia in Moral and Value Judgments of Large Language ModelsBruce W. Lee, Yeongheon Lee, Hyunsoo ChoACL 2026 · 5 citations
- Large Language Models Assume People are More Rational than We Really areRyan Liu, Jiayi Geng, Joshua C. Peterson, Ilia Sucholutsky et al.ICLR 2025
