"The results show that those impressions are highly sensitive to how the model presents itself. Warmth - essentially how friendly and personable the chatbot seems - significantly impacted all perceptions of LLM, including anthropomorphism, trust, usefulness, similarity, frustration, and closeness."
"Competence does what you'd expect: it makes the thing seem useful. It drives the bits tied to getting stuff right - trust, usefulness, not wanting to throw your laptop out the window. What it doesn't do is make the model feel human."
"Crank up the friendliness, and people start reacting to the bot less like software and more like something with a personality - and not necessarily a good one. Too much friendliness without the substance to back it up can tip into superficial agreeableness."
A study analyzed over 2,000 human-chatbot interactions to determine how warmth, competence, and empathy influence perceptions of large language models (LLMs). Findings indicate that warmth significantly affects users' views on LLMs, impacting trust, usefulness, and feelings of closeness. While competence is important for utility, it does not enhance the perception of human-like qualities. Excessive friendliness without substance can lead to perceptions of superficiality. The study emphasizes the importance of warmth in fostering human-like interactions with chatbots.
Read at Theregister
Unable to calculate read time
Collection
[
|
...
]