An appraisal-based chain-of-emotion architecture for affective language model game agents.
The development of believable, natural, and interactive digital artificial agents is a field of growing interest. Theoretical uncertainties and technical barriers present considerable challenges to the field, particularly with regards to developing agents that effectively simulate human emotions. La...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2024-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0301033&type=printable |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841555364898668544 |
|---|---|
| author | Maximilian Croissant Madeleine Frister Guy Schofield Cade McCall |
| author_facet | Maximilian Croissant Madeleine Frister Guy Schofield Cade McCall |
| author_sort | Maximilian Croissant |
| collection | DOAJ |
| description | The development of believable, natural, and interactive digital artificial agents is a field of growing interest. Theoretical uncertainties and technical barriers present considerable challenges to the field, particularly with regards to developing agents that effectively simulate human emotions. Large language models (LLMs) might address these issues by tapping common patterns in situational appraisal. In three empirical experiments, this study tests the capabilities of LLMs to solve emotional intelligence tasks and to simulate emotions. It presents and evaluates a new Chain-of-Emotion architecture for emotion simulation within video games, based on psychological appraisal research. Results show that it outperforms control LLM architectures on a range of user experience and content analysis metrics. This study therefore provides early evidence of how to construct and test affective agents based on cognitive processes represented in language models. |
| format | Article |
| id | doaj-art-16f6ff7138a84a65b845a8433f8a1283 |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-16f6ff7138a84a65b845a8433f8a12832025-01-08T05:33:35ZengPublic Library of Science (PLoS)PLoS ONE1932-62032024-01-01195e030103310.1371/journal.pone.0301033An appraisal-based chain-of-emotion architecture for affective language model game agents.Maximilian CroissantMadeleine FristerGuy SchofieldCade McCallThe development of believable, natural, and interactive digital artificial agents is a field of growing interest. Theoretical uncertainties and technical barriers present considerable challenges to the field, particularly with regards to developing agents that effectively simulate human emotions. Large language models (LLMs) might address these issues by tapping common patterns in situational appraisal. In three empirical experiments, this study tests the capabilities of LLMs to solve emotional intelligence tasks and to simulate emotions. It presents and evaluates a new Chain-of-Emotion architecture for emotion simulation within video games, based on psychological appraisal research. Results show that it outperforms control LLM architectures on a range of user experience and content analysis metrics. This study therefore provides early evidence of how to construct and test affective agents based on cognitive processes represented in language models.https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0301033&type=printable |
| spellingShingle | Maximilian Croissant Madeleine Frister Guy Schofield Cade McCall An appraisal-based chain-of-emotion architecture for affective language model game agents. PLoS ONE |
| title | An appraisal-based chain-of-emotion architecture for affective language model game agents. |
| title_full | An appraisal-based chain-of-emotion architecture for affective language model game agents. |
| title_fullStr | An appraisal-based chain-of-emotion architecture for affective language model game agents. |
| title_full_unstemmed | An appraisal-based chain-of-emotion architecture for affective language model game agents. |
| title_short | An appraisal-based chain-of-emotion architecture for affective language model game agents. |
| title_sort | appraisal based chain of emotion architecture for affective language model game agents |
| url | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0301033&type=printable |
| work_keys_str_mv | AT maximiliancroissant anappraisalbasedchainofemotionarchitectureforaffectivelanguagemodelgameagents AT madeleinefrister anappraisalbasedchainofemotionarchitectureforaffectivelanguagemodelgameagents AT guyschofield anappraisalbasedchainofemotionarchitectureforaffectivelanguagemodelgameagents AT cademccall anappraisalbasedchainofemotionarchitectureforaffectivelanguagemodelgameagents AT maximiliancroissant appraisalbasedchainofemotionarchitectureforaffectivelanguagemodelgameagents AT madeleinefrister appraisalbasedchainofemotionarchitectureforaffectivelanguagemodelgameagents AT guyschofield appraisalbasedchainofemotionarchitectureforaffectivelanguagemodelgameagents AT cademccall appraisalbasedchainofemotionarchitectureforaffectivelanguagemodelgameagents |