ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks · HackerPapers discussions

ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks — mentioned by famouswaffles

Wed, 13 Sep 2023 15:38:18 GMT

LLMs are better at that though. Sure you may not require them but it certainly wouldn't be for a lack of accuracy. https://www.artisana.ai/articles/gpt-4-outperforms-elite-cro... https://arxiv.org/abs/2303.15056

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

ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks — mentioned by famouswaffles

Tue, 11 Jul 2023 19:15:42 GMT

Current State of the art (GPT-4) is mostly on par with experts and much better than crowdworkers. Might be overkill though. https://www.artisana.ai/articles/gpt-4-outperforms-elite-cro... 3.5 (what is used here) is better than crowd workers https://arxiv.org/abs/2303.15056

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

ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks — mentioned by famouswaffles

Fri, 07 Jul 2023 12:18:28 GMT

Or just use the tools directly since they no longer underperform human actors. GPT-4 going toe to toe with the experts who set the benchmarks, way overperforming the crowdworkers https://www.artisana.ai/articles/gpt-4-outperforms-elite-cro... GPT-3.5 outperforming crowdworkers https://arxiv.org/abs/2303.15056 More money won't stop people from automating whatever they can. Especially when the automation provides such good results.

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

ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks — mentioned by famouswaffles

Wed, 28 Jun 2023 19:37:59 GMT

>should you just cut out the middle-model and be using ChatGPT as your classifier? Oh you certainly could. See here: GPT-3.5 outperforming elite crowdworkers on MTurk for Text annotation https://arxiv.org/abs/2303.15056 GPT-4 going toe to toe with expertrs (and significantly outperforming crowdworkers) on NLP tasks https://www.artisana.ai/articles/gpt-4-outperforms-elite-cro... I guess it will tke some time before the reality really sinks but the days of the artificial sota being obviously behind human efforts for NLP has come and gone.

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

ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks — mentioned by famouswaffles

Wed, 14 Jun 2023 17:20:42 GMT

There's the paper that shows ChatGPT outperforming MTurk Crowdworkers and another one showing GPT-4 going to to toe with experts (and blowing past crowdworkers) who set the benchmarks they were evaluating. https://arxiv.org/abs/2303.15056 https://www.artisana.ai/articles/gpt-4-outperforms-elite-cro... If quality is the issue then rest easy lol. The age of state of the art artificial Natural Language Processers being obviously inferior to Human Performance has come and gone.

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

ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks — HN submission

Tue, 28 Mar 2023 01:39:02 GMT

ChatGPT outperforms crowd-workers for text-annotation tasks

240 points; 205 discussion replies on HN. Paper and source history. A submission is not an endorsement.