LLM-based ambiguity detection in natural language instructions for collaborative surgical robots
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912484326113280 |
|---|---|
| author | Davila, Ana Colan, Jacinto Hasegawa, Yasuhisa |
| author_facet | Davila, Ana Colan, Jacinto Hasegawa, Yasuhisa |
| contents | Ambiguity in natural language instructions poses significant risks in safety-critical human-robot interaction, particularly in domains such as surgery. To address this, we propose a framework that uses Large Language Models (LLMs) for ambiguity detection specifically designed for collaborative surgical scenarios. Our method employs an ensemble of LLM evaluators, each configured with distinct prompting techniques to identify linguistic, contextual, procedural, and critical ambiguities. A chain-of-thought evaluator is included to systematically analyze instruction structure for potential issues. Individual evaluator assessments are synthesized through conformal prediction, which yields non-conformity scores based on comparison to a labeled calibration dataset. Evaluating Llama 3.2 11B and Gemma 3 12B, we observed classification accuracy exceeding 60% in differentiating ambiguous from unambiguous surgical instructions. Our approach improves the safety and reliability of human-robot collaboration in surgery by offering a mechanism to identify potentially ambiguous instructions before robot action. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_11525 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLM-based ambiguity detection in natural language instructions for collaborative surgical robots Davila, Ana Colan, Jacinto Hasegawa, Yasuhisa Robotics Human-Computer Interaction Ambiguity in natural language instructions poses significant risks in safety-critical human-robot interaction, particularly in domains such as surgery. To address this, we propose a framework that uses Large Language Models (LLMs) for ambiguity detection specifically designed for collaborative surgical scenarios. Our method employs an ensemble of LLM evaluators, each configured with distinct prompting techniques to identify linguistic, contextual, procedural, and critical ambiguities. A chain-of-thought evaluator is included to systematically analyze instruction structure for potential issues. Individual evaluator assessments are synthesized through conformal prediction, which yields non-conformity scores based on comparison to a labeled calibration dataset. Evaluating Llama 3.2 11B and Gemma 3 12B, we observed classification accuracy exceeding 60% in differentiating ambiguous from unambiguous surgical instructions. Our approach improves the safety and reliability of human-robot collaboration in surgery by offering a mechanism to identify potentially ambiguous instructions before robot action. |
| title | LLM-based ambiguity detection in natural language instructions for collaborative surgical robots |
| topic | Robotics Human-Computer Interaction |
| url | https://arxiv.org/abs/2507.11525 |