# Sniff AI: Is My 'Spicy' Your 'Spicy'? Exploring LLM's Perceptual Alignment with Human Smell Experiences

arXiv: https://arxiv.org/abs/2411.06950 · HTML: https://mlsanity.com/paper/2411.06950/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2024.

## Built on by (most cited first, 7 of 7)

- [Levels of Analysis for Large Language Models](https://mlsanity.com/paper/2503.13401/) (2025)
- [The Zero Body Problem: Probing LLM Use of Sensory Language](https://mlsanity.com/paper/2504.06393/) (2025)
- [Benchmark for Assessing Olfactory Perception of Large Language Models](https://mlsanity.com/paper/2604.00002/) (2026)
- [The Limits of Learning from Pictures and Text: Vision-Language Models and Embodied Scene Understanding](https://mlsanity.com/paper/2603.26589/) (2026)
- [AromaGen: Interactive Generation of Rich Olfactory Experiences with Multimodal Language Models](https://mlsanity.com/paper/2604.01650/) (2026)
- [NOSE: Neural Olfactory-Semantic Embedding with Tri-Modal Orthogonal Contrastive Learning](https://mlsanity.com/paper/2604.10452/) (2026)
- [Extracting Conceptual Spaces from LLMs Using Prototype Embeddings](https://mlsanity.com/paper/2509.19269/) (2025)

## Abstract (arXiv)

Aligning AI with human intent is important, yet perceptual alignment-how AI interprets what we see, hear, or smell-remains underexplored. This work focuses on olfaction, human smell experiences. We conducted a user study with 40 participants to investigate how well AI can interpret human descriptions of scents. Participants performed "sniff and describe" interactive tasks, with our designed AI system attempting to guess what scent the participants were experiencing based on their descriptions. These tasks evaluated the Large Language Model's (LLMs) contextual understanding and representation of scent relationships within its internal states - high-dimensional embedding space. Both quantitative and qualitative methods were used to evaluate the AI system's performance. Results indicated limited perceptual alignment, with biases towards certain scents, like lemon and peppermint, and continued failing to identify others, like rosemary. We discuss these findings in light of human-AI alignment advancements, highlighting the limitations and opportunities for enhancing HCI systems with multisensory experience integration.