mlsanityData to 14 Oct 2026

The Zero Body Problem: Probing LLM Use of Sensory Language

arXiv 2504.06393 ↗First posted 8 Apr 2025cs.CL cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Sensory language expresses embodied experiences ranging from taste and sound to excitement and stomachache. This language is of interest to scholars from a wide range of domains including robotics, narratology, linguistics, and cognitive science. In this work, we explore whether language models, which are not embodied, can approximate human use of embodied language. We extend an existing corpus of parallel human and model responses to short story prompts with an additional 18,000 stories generated by 18 popular models. We find that all models generate stories that differ significantly from human usage of sensory language, but the direction of these differences varies considerably between model families. Namely, Gemini models use significantly more sensory language than humans along most axes whereas most models from the remaining five families use significantly less. Linear probes run on five models suggest that they are capable of identifying sensory language. However, we find preliminary evidence suggesting that instruction tuning may discourage usage of sensory language. Finally, to support further work, we release our expanded story dataset.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 22 of its 44 references that are in the map. First posted on arXiv 8 Apr 2025.

Builds on

22 of 44 references.

References · 22

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2024Qwen2.5 Technical Reportcited by 4,942
  5. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  6. 2018Hierarchical Neural Story Generationcited by 1,193
  7. 2019BERT Rediscovers the Classical NLP Pipelinecited by 1,059
  8. 2023The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasetscited by 712
  9. 2023Language Models Represent Space and Timecited by 316
  10. 2021Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Colorcited by 119
  11. 2024GroundingGPT:Language Enhanced Multi-modal Grounding Modelcited by 101
  12. 2023Large language models predict human sensory judgments across six modalitiescited by 48
10 more
  1. 2022Visual Commonsense in Pretrained Unimodal and Multimodal Modelscited by 39
  2. 2021The World of an Octopus: How Reporting Bias Influences a Language Model's Perception of Colorcited by 32
  3. 2015Symbol Emergence in Robotics: A Surveycited by 31
  4. 2023Gromov-Wasserstein unsupervised alignment reveals structural correspondences between the color similarity structures of humans and large language modelscited by 16
  5. 2024What Do Language Models Hear? Probing for Auditory Representations in Language Modelscited by 15
  6. 2024Sniff AI: Is My 'Spicy' Your 'Spicy'? Exploring LLM's Perceptual Alignment with Human Smell Experiencescited by 7
  7. 2024Language Models Don't Learn the Physical Manifestation of Languagecited by 4
  8. 2025Exploring Multimodal Perception in Large Language Models Through Perceptual Strength Ratingscited by 3
  9. 2024TouchAI: Exploring human-AI perceptual alignment in touch through language model representationscited by 2
  10. 2023The language of sounds unheard: Exploring musical timbre semantics of large language modelscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025NarraBench: A Comprehensive Framework for Narrative Benchmarkingcited by 13
  2. 2026The Limits of Learning from Pictures and Text: Vision-Language Models and Embodied Scene Understandingcited by 2
  3. 2026AI as a Tool for Simulation-Based Experiments in Literary Studiescited by 2
  4. 2026How LLMs Build Fictional Worlds: Setting and Narrative Space in AI-Generated Creative Storytellingcited by 0
  5. 2026Where Does the Sound Go? Tracing Acoustic Information Loss in Audio-Conditioned LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Does Visual Grounding Enhance the Understanding of Embodied Knowledge in Large Language Models?
  2. 2024Exploring Spatial Schema Intuitions in Large Language and Vision Models
  3. 2026Where Should Language Sit in a Multimodal Model? Lessons from What Language Does to Human Perception and Cognition
  4. 2025Language Models Might Not Understand You: Evaluating Theory of Mind via Story Prompting
  5. 2023Psychometric Predictive Power of Large Language Models
  6. 2023Divergences between Language Models and Human Brains
  7. 2024With Ears to See and Eyes to Hear: Sound Symbolism Experiments with Multimodal Large Language Models
  8. 2025To Embody or Not: The Effect Of Embodiment On User Perception Of LLM-based Conversational Agents