Are they lovers or friends? Evaluating LLMs' Social Reasoning in English and Korean Dialogues
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_ | 1866915944043905024 |
|---|---|
| author | Kim, Eunsu Park, Junyeong Oh, Juhyun Park, Kiwoong Song, Seyoung Doğruöz, A. Seza Oh, Alice Kim, Najoung |
| author_facet | Kim, Eunsu Park, Junyeong Oh, Juhyun Park, Kiwoong Song, Seyoung Doğruöz, A. Seza Oh, Alice Kim, Najoung |
| contents | As LLMs are increasingly deployed in real-world interactions, their social reasoning in interpersonal communication becomes critical. To explore their capabilities, we introduce SCRIPTS, a 1.1k-dialogue dataset in English and Korean, sourced from movie scripts and propose a social reasoning task based on SCRIPTS that evaluates the capacity of LLMs to infer the social relationships (e.g., friends, lovers) between speakers in each dialogue. Evaluating nine models on our task, current LLMs achieve around 75--80% on the English dataset and 58--69% in Korean, and models predict an Unlikely relationship in 10--25% of responses in both languages. Furthermore, we find that thinking models and chain-of-thought prompting provide minimal benefits for social reasoning and occasionally amplify social biases. In sum, there are significant limitations in current LLMs' social reasoning capabilities, especially for Korean, highlighting the need for efforts to develop socially-aware LLMs across languages. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_19028 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Are they lovers or friends? Evaluating LLMs' Social Reasoning in English and Korean Dialogues Kim, Eunsu Park, Junyeong Oh, Juhyun Park, Kiwoong Song, Seyoung Doğruöz, A. Seza Oh, Alice Kim, Najoung Computation and Language As LLMs are increasingly deployed in real-world interactions, their social reasoning in interpersonal communication becomes critical. To explore their capabilities, we introduce SCRIPTS, a 1.1k-dialogue dataset in English and Korean, sourced from movie scripts and propose a social reasoning task based on SCRIPTS that evaluates the capacity of LLMs to infer the social relationships (e.g., friends, lovers) between speakers in each dialogue. Evaluating nine models on our task, current LLMs achieve around 75--80% on the English dataset and 58--69% in Korean, and models predict an Unlikely relationship in 10--25% of responses in both languages. Furthermore, we find that thinking models and chain-of-thought prompting provide minimal benefits for social reasoning and occasionally amplify social biases. In sum, there are significant limitations in current LLMs' social reasoning capabilities, especially for Korean, highlighting the need for efforts to develop socially-aware LLMs across languages. |
| title | Are they lovers or friends? Evaluating LLMs' Social Reasoning in English and Korean Dialogues |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2510.19028 |