# Inertia in Moral and Value Judgments of Large Language Models

arXiv: https://arxiv.org/abs/2408.09049 · HTML: https://mlsanity.com/paper/2408.09049/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 56 references that are in the map.
- First posted on arXiv 16 Aug 2024.

## Builds on (most cited first, 24 of 24)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study](https://mlsanity.com/paper/2303.17466/) (2023)
- [InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews](https://mlsanity.com/paper/2310.17976/) (2023)
- [Towards Measuring and Modeling "Culture" in LLMs: A Survey](https://mlsanity.com/paper/2403.15412/) (2024)
- [Cognitive Bias in Decision-Making with LLMs](https://mlsanity.com/paper/2403.00811/) (2024)
- [NLPositionality: Characterizing Design Biases of Datasets and Models](https://mlsanity.com/paper/2306.01943/) (2023)
- [Evaluating Large Language Model Biases in Persona-Steered Generation](https://mlsanity.com/paper/2405.20253/) (2024)
- [Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles](https://mlsanity.com/paper/2407.00870/) (2024)
- [Beyond prompt brittleness: Evaluating the reliability and consistency of political worldviews in LLMs](https://mlsanity.com/paper/2402.17649/) (2024)
- [Character is Destiny: Can Role-Playing Language Agents Make Persona-Driven Decisions?](https://mlsanity.com/paper/2404.12138/) (2024)
- [PsychoGAT: A Novel Psychological Measurement Paradigm through Interactive Fiction Games with LLM Agents](https://mlsanity.com/paper/2402.12326/) (2024)
- [Aligning Large Language Models with Human Opinions through Persona Selection and Value--Belief--Norm Reasoning](https://mlsanity.com/paper/2311.08385/) (2023)
- [How Well Can LLMs Echo Us? Evaluating AI Chatbots' Role-Play Ability with ECHO](https://mlsanity.com/paper/2404.13957/) (2024)
- [LLM Roleplay: Simulating Human-Chatbot Interaction](https://mlsanity.com/paper/2407.03974/) (2024)
- [Stick to your Role! Stability of Personal Values Expressed in Large Language Models](https://mlsanity.com/paper/2402.14846/) (2024)
- [The Drama Machine: Simulating Character Development with LLM Agents](https://mlsanity.com/paper/2408.01725/) (2024)

## Built on by (most cited first, 2 of 2)

- [Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas](https://mlsanity.com/paper/2505.14633/) (2025)
- [When Do LLM Preferences Predict Downstream Behavior?](https://mlsanity.com/paper/2602.18971/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) behave non-deterministically, and prompting has become a common method for steering their outputs. A popular strategy is to assign a persona to the model to produce more varied, context-sensitive responses, similar to how responses vary across human individuals. Against the expectation that persona prompting yields a wide range of opinions, our experiments show that LLMs keep consistent value orientations. We observe a persistent inertia in their responses, where certain moral and value dimensions (especially harm avoidance and fairness) stay skewed in one direction across persona settings. To study this, we use role-play at scale, which pairs randomized persona prompts with a macro-level analysis of model outputs. Our results point to strong internal biases and value preferences in LLMs, which we call value orientation and inertia. These models warrant scrutiny and adjustment before use in applications where balanced outputs matter.