# Post-training makes large language models less human-like

arXiv: https://arxiv.org/abs/2605.07632 · HTML: https://mlsanity.com/paper/2605.07632/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 132 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 30 of 32)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Using cognitive psychology to understand GPT-3](https://mlsanity.com/paper/2206.14576/) (2022)
- [Understanding the Effects of RLHF on LLM Generalisation and Diversity](https://mlsanity.com/paper/2310.06452/) (2023)
- [Playing repeated games with Large Language Models](https://mlsanity.com/paper/2305.16867/) (2023)
- [Mitigating the Alignment Tax of RLHF](https://mlsanity.com/paper/2309.06256/) (2023)
- [In-Context Impersonation Reveals Large Language Models' Strengths and Biases](https://mlsanity.com/paper/2305.14930/) (2023)
- [Thinking Fast and Slow in Large Language Models](https://mlsanity.com/paper/2212.05206/) (2022)
- [Why Does Surprisal From Larger Transformer-Based Language Models Provide a Poorer Fit to Human Reading Times?](https://mlsanity.com/paper/2212.12131/) (2022)
- [A fine-grained comparison of pragmatic language understanding in humans and language models](https://mlsanity.com/paper/2212.06801/) (2022)
- [Do LLMs write like humans? Variation in grammatical and rhetorical styles](https://mlsanity.com/paper/2410.16107/) (2024)
- [Language models align with human judgments on key grammatical constructions](https://mlsanity.com/paper/2402.01676/) (2024)
- [Large language models predict human sensory judgments across six modalities](https://mlsanity.com/paper/2302.01308/) (2023)
- [Testing AI on language comprehension tasks reveals insensitivity to underlying meaning](https://mlsanity.com/paper/2302.12313/) (2023)
- [The Prompt Makes the Person(a): A Systematic Evaluation of Sociodemographic Persona Prompting for Large Language Models](https://mlsanity.com/paper/2507.16076/) (2025)
- [HumanLM: Simulating Users with State Alignment Beats Response Imitation](https://mlsanity.com/paper/2603.03303/) (2026)
- [This human study did not involve human subjects: Validating LLM simulations as behavioral evidence](https://mlsanity.com/paper/2602.15785/) (2026)
- [The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling Probabilistic Social Inferences from Linguistic Inputs](https://mlsanity.com/paper/2306.14325/) (2023)
- [Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex](https://mlsanity.com/paper/2306.03779/) (2023)
- [Capturing the Complexity of Human Strategic Decision-Making with Machine Learning](https://mlsanity.com/paper/2408.07865/) (2024)
- [Large Language Models show both individual and collective creativity comparable to humans](https://mlsanity.com/paper/2412.03151/) (2024)
- [Bayesian Statistical Modeling with Predictors from LLMs](https://mlsanity.com/paper/2406.09012/) (2024)
- [Evaluating alignment between humans and neural network representations in image-based learning tasks](https://mlsanity.com/paper/2306.09377/) (2023)
- [Psychometric Predictive Power of Large Language Models](https://mlsanity.com/paper/2311.07484/) (2023)
- [Evaluating Language Models' Evaluations of Games](https://mlsanity.com/paper/2510.10930/) (2025)
- [Synthetic Interaction Data for Scalable Personalization in Large Language Models](https://mlsanity.com/paper/2602.12394/) (2026)

## Built on by (most cited first, 5 of 5)

- [Apparent Psychological Profiles of Large Language Models are Largely a Measurement Artifact](https://mlsanity.com/paper/2606.20205/) (2026)
- [Small Foundation Models of Human Cognition and Behaviour](https://mlsanity.com/paper/2608.05224/) (2026)
- [Architecture-Sensitive Supervised Fine-Tuning for Screen-Conditioned Action Prediction: A PiSAR Benchmark](https://mlsanity.com/paper/2605.29400/) (2026)
- [Pretrained Persona Mixture Models and Tandem Models for Human Simulation](https://mlsanity.com/paper/2609.22607/) (2026)
- [Are Human-Aligned Models Models of Humans? A Turing-Test Gap in Preference Alignment](https://mlsanity.com/paper/2609.23640/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used as surrogates for human participants, but it remains unclear which models best capture human behavior and why. To address this, we introduce Psych-201, a novel dataset that enables us to measure behavioral alignment at scale. We find that post-training -- the stage that turns base models into useful assistants -- consistently reduces alignment with human behavior across model families, sizes, and objectives. Moreover, this misalignment widens in newer model generations even as base models continue to improve. Finally, we find that persona-induction -- a popular technique for eliciting human-like behavior by conditioning models on participant-specific information -- does not improve predictions at the level of individuals. Taken together, our results suggest that the very processes that are currently employed to turn LLMs into useful assistants also make them less accurate models of human behavior.