# Where Norms and References Collide: Evaluating LLMs on Normative Reasoning

arXiv: https://arxiv.org/abs/2602.02975 · HTML: https://mlsanity.com/paper/2602.02975/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 14 of its 32 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 14 of 14)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [Social Chemistry 101: Learning to Reason about Social and Moral Norms](https://mlsanity.com/paper/2011.00620/) (2020)
- [AI Agents That Matter](https://mlsanity.com/paper/2407.01502/) (2024)
- [Granite Code Models: A Family of Open Foundation Models for Code Intelligence](https://mlsanity.com/paper/2405.04324/) (2024)
- [ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models](https://mlsanity.com/paper/2303.16421/) (2023)
- [SocialIQA: Commonsense Reasoning about Social Interactions](https://mlsanity.com/paper/1904.09728/) (2019)
- [LLMs for Robotic Object Disambiguation](https://mlsanity.com/paper/2401.03388/) (2024)
- [A Defeasible Deontic Calculus for Resolving Norm Conflicts](https://mlsanity.com/paper/2407.04869/) (2024)

## Built on by (most cited first, 3 of 3)

- [Rule vs.Consequence: Dissociable Internal Representations of Moral Reasoning in LLMs](https://mlsanity.com/paper/2610.16371/) (2026)
- [Naturalistic measure of social norms alignment](https://mlsanity.com/paper/2605.23420/) (2026)
- [Who Owns That? Evaluating Ownership Intuitions in Large Language Models](https://mlsanity.com/paper/2609.39483/) (2026)

## Abstract (arXiv)

Embodied agents, such as robots, will need to interact in situated environments where successful communication often depends on reasoning over social norms: shared expectations that constrain what actions are appropriate in context. A key capability in such settings is norm-based reference resolution (NBRR), where interpreting referential expressions requires inferring implicit normative expectations grounded in physical and social context. Yet it remains unclear whether Large Language Models (LLMs) can support this kind of reasoning. In this work, we introduce SNIC (Situated Norms in Context), a human-validated diagnostic testbed designed to probe how well state-of-the-art LLMs can extract and utilize normative principles relevant to NBRR. SNIC emphasizes physically grounded norms that arise in everyday tasks such as cleaning, tidying, and serving. Across a range of controlled evaluations, we find that even the strongest LLMs struggle to consistently identify and apply social norms, particularly when norms are implicit, underspecified, or in conflict. These findings reveal a blind spot in current LLMs and highlight a key challenge for deploying language-based systems in socially situated, embodied settings.