Zobraziť v EDS

When large language models are reliable for judging empathic communication.

Uložené v:
Podrobná bibliografia
Názov: When large language models are reliable for judging empathic communication.
Autori: Kumar, Aakriti, Poungpeth, Nalin, Yang, Diyi, Farrell, Erina, Lambert, Bruce L., Groh, Matthew
Zdroj: Nature Machine Intelligence; Feb2026, Vol. 8 Issue 2, p173-185, 13p
Abstrakt: Large language models (LLMs) excel at generating empathic responses in text-based conversations. But, how reliably do they judge the nuances of empathic communication? Here we investigate this question by comparing how experts, crowdworkers and LLMs annotate empathic communication across four evaluative frameworks drawn from psychology, natural language processing and communications applied to 200 real-world conversations where one speaker shares a personal problem and the other offers support. Drawing on 3,150 expert annotations, 2,844 crowd annotations and 3,150 LLM annotations, we assess interrater reliability between these three annotator groups. We find that expert agreement is high but varies across the frameworks' subcomponents depending on their clarity, complexity and subjectivity. We show that expert agreement offers a more informative benchmark for contextualizing LLM performance than standard classification metrics. Across all four frameworks, LLMs consistently approach this expert level benchmark and exceed the reliability of crowdworkers. These results demonstrate how LLMs, when validated on specific tasks with appropriate benchmarks, can support transparency and oversight in emotionally sensitive applications including their use as conversational companions. Kumar et al. show that large language models (LLMs) nearly match expert reliability and outperform laypeople when assessing empathic communication across multiple frameworks. The performance of both LLMs and experts depends on clear and specific evaluation criteria. [ABSTRACT FROM AUTHOR]
Copyright of Nature Machine Intelligence is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Databáza: Biomedical Index
Popis
Abstrakt:Large language models (LLMs) excel at generating empathic responses in text-based conversations. But, how reliably do they judge the nuances of empathic communication? Here we investigate this question by comparing how experts, crowdworkers and LLMs annotate empathic communication across four evaluative frameworks drawn from psychology, natural language processing and communications applied to 200 real-world conversations where one speaker shares a personal problem and the other offers support. Drawing on 3,150 expert annotations, 2,844 crowd annotations and 3,150 LLM annotations, we assess interrater reliability between these three annotator groups. We find that expert agreement is high but varies across the frameworks' subcomponents depending on their clarity, complexity and subjectivity. We show that expert agreement offers a more informative benchmark for contextualizing LLM performance than standard classification metrics. Across all four frameworks, LLMs consistently approach this expert level benchmark and exceed the reliability of crowdworkers. These results demonstrate how LLMs, when validated on specific tasks with appropriate benchmarks, can support transparency and oversight in emotionally sensitive applications including their use as conversational companions. Kumar et al. show that large language models (LLMs) nearly match expert reliability and outperform laypeople when assessing empathic communication across multiple frameworks. The performance of both LLMs and experts depends on clear and specific evaluation criteria. [ABSTRACT FROM AUTHOR]
ISSN:25225839
DOI:10.1038/s42256-025-01169-6