paper-with-me

Papers

Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies

2022-08-18 · Gati Aher, Rosa I. Arriaga, Adam Tauman Kalai

We introduce a new type of test, called a Turing Experiment (TE), for evaluating to what extent a given language model, such as GPT models, can simulate different aspects of human behavior. A TE can also reveal consistent distortions in a language model's simulation of a specific human behavior. Unlike the Turing Test, which involves simulating a single arbitrary individual, a TE requires simulating a representative sample of participants in human subject research. We carry out TEs that attempt to replicate well-established findings from prior studies. We design a methodology for simulating TEs and illustrate its use to compare how well different language models are able to reproduce classic economic, psycholinguistic, and social psychology experiments: Ultimatum Game, Garden Path Sentences, Milgram Shock Experiment, and Wisdom of Crowds. In the first three TEs, the existing findings were replicated using recent models, while the last TE reveals a "hyper-accuracy distortion" present in some language models (including ChatGPT and GPT-4), which could affect downstream applications in education and the arts.

📄 PDF Abstract BibTeX arXiv:2208.10264

Code (2)

gatiaher/using-large-language-models-to-replicate-human-subject-studies 공식 구현
microsoft/turing-experiments

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…
GPT GPT is a Transformer-based architecture and training procedure for natural language processing tasks. Training follows a…
Test 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

LLM Agents Display Human Biases but Exhibit Distinct Learning Patterns

2025-03-13 · Idan Horowitz, Ori Plonsky

We investigate the choice patterns of Large Language Models (LLMs) in the context of Decisions from Experience tasks that involve repeated choice and learning from feedback, and compare their behavior to human participan…

Decision Making

TraderTalk: An LLM Behavioural ABM applied to Simulating Human Bilateral Trading Interactions

2024-10-10 · Alicia Vidler, Toby Walsh

We introduce a novel hybrid approach that augments Agent-Based Models (ABMs) with behaviors generated by Large Language Models (LLMs) to simulate human trading interactions. We call our model TraderTalk. Leveraging LLMs …

Training Socially Aligned Language Models on Simulated Social Interactions

2023-05-26 · Ruibo Liu, Ruixin Yang, Chenyan Jia, Ge Zhang 외

Social alignment in AI systems aims to ensure that these models behave according to established societal values. However, unlike humans, who derive consensus on value judgments through social interaction, current languag…

Hypothesis Testing for Quantifying LLM-Human Misalignment in Multiple Choice Settings

2025-06-17 · Harbin Hong, Sebastian Caldas, Liu Leqi

As Large Language Models (LLMs) increasingly appear in social science research (e.g., economics and marketing), it becomes crucial to assess how well these models replicate human behavior. In this work, using hypothesis …

Decision MakingLanguage ModelingLanguage ModellingMarketing+1

Evolution and compression in LLMs: On the emergence of human-aligned categorization

2025-09-09 · Nathaniel Imel, Noga Zaslavsky arxiv

Converging evidence suggests that human systems of semantic categories achieve near-optimal compression via the Information Bottleneck (IB) complexity-accuracy tradeoff. Large language models (LLMs) are not trained for t…