On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial · HackerPapers discussions

On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial — HN submission

Thu, 18 Jul 2024 18:29:40 GMT

The Conversational Persuasiveness of LLMs: A Randomized Controlled Trial

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial — mentioned by FeepingCreature

Fri, 12 Apr 2024 21:39:32 GMT

Less than a month ago: https://arxiv.org/abs/2403.14380 "We found that participants who debated GPT-4 with access to their personal information had 81.7% (p < 0.01; N=820 unique participants) higher odds of increased agreement with their opponents compared to participants who debated humans." And it's only gonna get better.

Paper and discussion history. A mention is not an endorsement.

On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial — mentioned by notachatbot1234

Thu, 11 Apr 2024 07:15:33 GMT

ChatGPT can better persuade people to believe lies, if it has information about them: https://arxiv.org/abs/2403.14380

Paper and discussion history. A mention is not an endorsement.

On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial — mentioned by throwaway888abc

Tue, 02 Apr 2024 22:33:41 GMT

[Submitted on 21 Mar 2024] On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial https://arxiv.org/abs/2403.14380

Paper and discussion history. A mention is not an endorsement.

On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial — HN submission

Fri, 22 Mar 2024 21:45:23 GMT

Study on Persuasiveness of LLMs

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.