Enhancing situation awareness through model-based explanation generation

Konstantinos Gavriilidis; Ioannis Konstas; Helen Hastie; Andrea Munafo; Wei Pang

Enhancing situation awareness through model-based explanation generation

Konstantinos Gavriilidis, Ioannis Konstas, Helen Hastie, Andrea Munafo, Wei Pang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

Robots are often deployed in remote locations for tasks such as exploration, where users cannot directly perceive the agent and its environment. For Human-In-The-Loop applications, operators must have a comprehensive understanding of the robot’s current state and its environment to take necessary actions and effectively assist the agent. In this work, we compare different explanation styles to determine the most effective way to convey real-time updates to users. Additionally, we formulate these explanation styles as separate fine-tuning tasks and assess the effectiveness of large language models in delivering in-mission updates to maintain situation awareness.

Original language	English
Title of host publication	Proceedings of the 2nd Workshop on Practical LLM-assisted Data-to-Text Generation
Editors	Simone Balloccu, Zdeněk Kasner, Ondřej Plátek, Patrícia Schmidtová, Kristýna Onderková, Mateusz Lango, Ondřej Dušek, Lucie Flek, Ehud Reiter, Dimitra Gkatzia, Simon Mille
Publisher	Association for Computational Linguistics
Pages	7-16
Number of pages	10
ISBN (Electronic)	9798891761261
Publication status	Published - 24 Sept 2024
Event	The 2nd Workshop on Practical LLM-assisted Data-to-Text Generation - Tokyo, Japan Duration: 23 Sept 2024 → 23 Sept 2024 https://practicald2t.github.io/

Workshop

Workshop	The 2nd Workshop on Practical LLM-assisted Data-to-Text Generation
Abbreviated title	Practical D2T 2024
Country/Territory	Japan
City	Tokyo
Period	23/09/24 → 23/09/24
Internet address	https://practicald2t.github.io/

Access to Document

GavriilidisEtalPracticalD2T2024EnhancingSituationAwarenessFinal published version, 5.18 MBLicence: Creative Commons: Attribution (CC-BY)

https://aclanthology.org/2024.practicald2t-1.2Licence: Creative Commons: Attribution (CC-BY)

Cite this

Gavriilidis, K., Konstas, I., Hastie, H., Munafo, A., & Pang, W. (2024). Enhancing situation awareness through model-based explanation generation. In S. Balloccu, Z. Kasner, O. Plátek, P. Schmidtová, K. Onderková, M. Lango, O. Dušek, L. Flek, E. Reiter, D. Gkatzia, & S. Mille (Eds.), Proceedings of the 2nd Workshop on Practical LLM-assisted Data-to-Text Generation (pp. 7-16). Association for Computational Linguistics. https://aclanthology.org/2024.practicald2t-1.2

Gavriilidis, Konstantinos ; Konstas, Ioannis ; Hastie, Helen et al. / Enhancing situation awareness through model-based explanation generation. Proceedings of the 2nd Workshop on Practical LLM-assisted Data-to-Text Generation. editor / Simone Balloccu ; Zdeněk Kasner ; Ondřej Plátek ; Patrícia Schmidtová ; Kristýna Onderková ; Mateusz Lango ; Ondřej Dušek ; Lucie Flek ; Ehud Reiter ; Dimitra Gkatzia ; Simon Mille. Association for Computational Linguistics, 2024. pp. 7-16

@inproceedings{34fd065409b6461ebaf04b515e075904,

title = "Enhancing situation awareness through model-based explanation generation",

abstract = "Robots are often deployed in remote locations for tasks such as exploration, where users cannot directly perceive the agent and its environment. For Human-In-The-Loop applications, operators must have a comprehensive understanding of the robot{\textquoteright}s current state and its environment to take necessary actions and effectively assist the agent. In this work, we compare different explanation styles to determine the most effective way to convey real-time updates to users. Additionally, we formulate these explanation styles as separate fine-tuning tasks and assess the effectiveness of large language models in delivering in-mission updates to maintain situation awareness.",

author = "Konstantinos Gavriilidis and Ioannis Konstas and Helen Hastie and Andrea Munafo and Wei Pang",

year = "2024",

month = sep,

day = "24",

language = "English",

pages = "7--16",

editor = "Simone Balloccu and Zden{\v e}k Kasner and Ond{\v r}ej Pl{\'a}tek and Patr{\'i}cia Schmidtov{\'a} and Krist{\'y}na Onderkov{\'a} and Mateusz Lango and Ond{\v r}ej Du{\v s}ek and Lucie Flek and Ehud Reiter and Dimitra Gkatzia and Simon Mille",

booktitle = "Proceedings of the 2nd Workshop on Practical LLM-assisted Data-to-Text Generation",

publisher = "Association for Computational Linguistics",

note = "The 2nd Workshop on Practical LLM-assisted Data-to-Text Generation, Practical D2T 2024 ; Conference date: 23-09-2024 Through 23-09-2024",

url = "https://practicald2t.github.io/",

}

Gavriilidis, K, Konstas, I, Hastie, H, Munafo, A & Pang, W 2024, Enhancing situation awareness through model-based explanation generation. in S Balloccu, Z Kasner, O Plátek, P Schmidtová, K Onderková, M Lango, O Dušek, L Flek, E Reiter, D Gkatzia & S Mille (eds), Proceedings of the 2nd Workshop on Practical LLM-assisted Data-to-Text Generation. Association for Computational Linguistics, pp. 7-16, The 2nd Workshop on Practical LLM-assisted Data-to-Text Generation, Tokyo, Japan, 23/09/24. <https://aclanthology.org/2024.practicald2t-1.2>

Enhancing situation awareness through model-based explanation generation. / Gavriilidis, Konstantinos; Konstas, Ioannis; Hastie, Helen et al.
Proceedings of the 2nd Workshop on Practical LLM-assisted Data-to-Text Generation. ed. / Simone Balloccu; Zdeněk Kasner; Ondřej Plátek; Patrícia Schmidtová; Kristýna Onderková; Mateusz Lango; Ondřej Dušek; Lucie Flek; Ehud Reiter; Dimitra Gkatzia; Simon Mille. Association for Computational Linguistics, 2024. p. 7-16.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Enhancing situation awareness through model-based explanation generation

AU - Gavriilidis, Konstantinos

AU - Konstas, Ioannis

AU - Hastie, Helen

AU - Munafo, Andrea

AU - Pang, Wei

PY - 2024/9/24

Y1 - 2024/9/24

N2 - Robots are often deployed in remote locations for tasks such as exploration, where users cannot directly perceive the agent and its environment. For Human-In-The-Loop applications, operators must have a comprehensive understanding of the robot’s current state and its environment to take necessary actions and effectively assist the agent. In this work, we compare different explanation styles to determine the most effective way to convey real-time updates to users. Additionally, we formulate these explanation styles as separate fine-tuning tasks and assess the effectiveness of large language models in delivering in-mission updates to maintain situation awareness.

AB - Robots are often deployed in remote locations for tasks such as exploration, where users cannot directly perceive the agent and its environment. For Human-In-The-Loop applications, operators must have a comprehensive understanding of the robot’s current state and its environment to take necessary actions and effectively assist the agent. In this work, we compare different explanation styles to determine the most effective way to convey real-time updates to users. Additionally, we formulate these explanation styles as separate fine-tuning tasks and assess the effectiveness of large language models in delivering in-mission updates to maintain situation awareness.

M3 - Conference contribution

SP - 7

EP - 16

BT - Proceedings of the 2nd Workshop on Practical LLM-assisted Data-to-Text Generation

A2 - Balloccu, Simone

A2 - Kasner, Zdeněk

A2 - Plátek, Ondřej

A2 - Schmidtová, Patrícia

A2 - Onderková, Kristýna

A2 - Lango, Mateusz

A2 - Dušek, Ondřej

A2 - Flek, Lucie

A2 - Reiter, Ehud

A2 - Gkatzia, Dimitra

A2 - Mille, Simon

PB - Association for Computational Linguistics

T2 - The 2nd Workshop on Practical LLM-assisted Data-to-Text Generation

Y2 - 23 September 2024 through 23 September 2024

ER -

Gavriilidis K, Konstas I, Hastie H, Munafo A, Pang W. Enhancing situation awareness through model-based explanation generation. In Balloccu S, Kasner Z, Plátek O, Schmidtová P, Onderková K, Lango M, Dušek O, Flek L, Reiter E, Gkatzia D, Mille S, editors, Proceedings of the 2nd Workshop on Practical LLM-assisted Data-to-Text Generation. Association for Computational Linguistics. 2024. p. 7-16

Enhancing situation awareness through model-based explanation generation

Abstract / Description of output

Workshop

Access to Document

Fingerprint

Cite this