AI generates well-liked but templatic empathic responses

TL;DR

This paper investigates how Large Language Models (LLMs) produce highly formulaic empathic responses using a common template, which explains their perceived effectiveness in emotional support.

Contribution

It introduces a taxonomy of 10 empathic tactics and demonstrates that LLM responses predominantly follow a well-liked, structured template, unlike more diverse human responses.

Findings

LLM responses match a common template 83-90% of the time.

Template covers 81-92% of LLM responses when matched.

Human responses are more diverse than LLM responses.

Abstract

Recent research shows that greater numbers of people are turning to Large Language Models (LLMs) for emotional support, and that people rate LLM responses as more empathic than human-written responses. We suggest a reason for this success: LLMs have learned and consistently deploy a well-liked template for expressing empathy. We develop a taxonomy of 10 empathic language "tactics" that include validating someone's feelings and paraphrasing, and apply this taxonomy to characterize the language that people and LLMs produce when writing empathic responses. Across a set of 2 studies comparing a total of n = 3,265 AI-generated (by six models) and n = 1,290 human-written responses, we find that LLM responses are highly formulaic at a discourse functional level. We discovered a template -- a structured sequence of tactics -- that matches between 83--90% of LLM responses (and 60--83\% in a held out sample), and when those are matched, covers 81--92% of the response. By contrast, human-written responses are more diverse. We end with a discussion of implications for the future of AI-generated empathy.