SocialEval: Evaluating Social Intelligence of Large Language Models
This work addresses the need to assess LLMs' social intelligence and their discrepancy with humans, which is important for AI researchers and developers, though it is incremental as it builds on existing evaluation paradigms.
The authors tackled the problem of evaluating the social intelligence (SI) of large language models (LLMs) by proposing SocialEval, a bilingual benchmark that integrates outcome- and process-oriented evaluations using narrative scripts. Experiments showed that LLMs fall behind humans on SI evaluations, exhibit prosociality, and prefer positive social behaviors even when they lead to goal failure.
LLMs exhibit promising Social Intelligence (SI) in modeling human behavior, raising the need to evaluate LLMs' SI and their discrepancy with humans. SI equips humans with interpersonal abilities to behave wisely in navigating social interactions to achieve social goals. This presents an operational evaluation paradigm: outcome-oriented goal achievement evaluation and process-oriented interpersonal ability evaluation, which existing work fails to address. To this end, we propose SocialEval, a script-based bilingual SI benchmark, integrating outcome- and process-oriented evaluation by manually crafting narrative scripts. Each script is structured as a world tree that contains plot lines driven by interpersonal ability, providing a comprehensive view of how LLMs navigate social interactions. Experiments show that LLMs fall behind humans on both SI evaluations, exhibit prosociality, and prefer more positive social behaviors, even if they lead to goal failure. Analysis of LLMs' formed representation space and neuronal activations reveals that LLMs have developed ability-specific functional partitions akin to the human brain.