REVIEW 2 cited by
On the Effectiveness of Creating Conversational Agent Personalities Through Prompting
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In this work, we report on the effectiveness of our efforts to tailor the personality and conversational style of a conversational agent based on GPT-3.5 and GPT-4 through prompts. We use three personality dimensions with two levels each to create eight conversational agents archetypes. Ten conversations were collected per chatbot, of ten exchanges each, generating 1600 exchanges across GPT-3.5 and GPT-4. Using Linguistic Inquiry and Word Count (LIWC) analysis, we compared the eight agents on language elements including clout, authenticity, and emotion. Four language cues were significantly distinguishing in GPT-3.5, while twelve were distinguishing in GPT-4. With thirteen out of a total nineteen cues in LIWC appearing as significantly distinguishing, our results suggest possible novel prompting approaches may be needed to better suit the creation and evaluation of persistent conversational agent personalities or language styles.
Forward citations
Cited by 2 Pith papers
-
Promoting Online Safety by Simulating Unsafe Conversations with LLMs
A pair of language models, one acting as scammer and one as target, can simulate realistic scam conversations, but the paper presents no user evaluation of whether this improves scam resilience.
-
Curiosity by Design: An LLM-based Coding Assistant Asking Clarification Questions
A fine-tuned classifier and question generator let a small coding assistant detect under-specified prompts and ask for clarification, which users rated better than a baseline in a small study.
Discussion (0). Sign in to comment.