Research map / Large language models / Language, safety and interpretability
AmadeusGPT: a natural language interface for interactive animal behavioral analysis
Shaokai Ye, Jessy Lauer, Mu Zhou, Alexander Mathis, Mackenzie W Mathis
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Rephraser module that rewrites user queries into API-doc style (ablation) | AmadeusGPT · EPM OOD paraphrase robustness | success rate: 32% -> 88% | Improved |
| add Rephraser module (ablation) | AmadeusGPT · EPM OOD paraphrase robustness | tokens consumed: 5,002 -> 4,322 | Improved |
| rule-based task programs from LLM-generated code instead of learned representations | MABe 2022 Mouse Triplet · T5 chase | F1: 0.050 -> 0.274 | Improved |
| rule-based task programs instead of learned representations | MABe 2022 Mouse Triplet · T12 watching | F1: 0.191 -> 0.600 | Improved |
| rule-based task programs instead of learned representations | MABe 2022 Mouse Triplet · T6 close | F1: 0.708 -> 0.700 | No clear effect |
| rule-based task programs instead of learned representations | MABe 2022 Mouse Triplet · T9 oral_ear_contact | F1: 0.0084 -> 0.024 | No clear effect |
| remove long-term memory after context window overflows (ablation) | AmadeusGPT · interactive session recall of user-defined behavior | code correctness (qualitative) | Improved |
Closest papers by meaning
- Meow-Omni 1: A Multimodal Large Language Model for Feline Ethology (NeurIPS 2026 · similarity 0.87)
- Discovering Symbolic Cognitive Models from Human and Animal Behavior (ICML 2025 · similarity 0.86)
- Animal-Bench: Benchmarking Multimodal Video Models for Animal-centric Video Understanding (NeurIPS 2024 · similarity 0.85)
- MammAlps: A Multi-view Video Behavior Monitoring Dataset of Wild Mammals in the Swiss Alps (CVPR 2025 · similarity 0.85)
- AniMo: Species-Aware Model for Text-Driven Animal Motion Generation (CVPR 2025 · similarity 0.84)
- Position: Principles of Animal Cognition to Improve LLM Evaluations (ICML 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
