An ACL paper from the PhilHuman project looks at using experts vs non-experts in human evaluation. It concludes that the agreement between experts and non-experts is worse for texts from GPT3 than texts from GPT2; in other words, non-expert evaluation is less useful for high-quality texts produced by recent LLMs.
At this moment in time, chatGPT and other LLMs seem to be much better at the “language” side of data-to-text than the “content” side, Even on the language side, there are important caveats about real-world usage. Of course, the above may change as the technology improves.
Evaluation advice in one sentence: plan your experiments in advance, including details; keep your experiment as simple and standard as possible; do a pilot experiment first to make sure everything works; and be very careful when you run the main experiment.
This year I was both a TACL Action Editor and an ACL Senior Area Chair. This experience has reinforced my belief that the journal review process is better!
We may see a big change in NLG evaluation over the next few years, with LLM-based evaluation replacing metrics such as BLEU and BLEURT, and a renewed emphasis on high-quality human evaluation to assess semantic and pragmatic correctness. Would be a step forward if this happens!
Many problems in NLP papers can *not* be detected by reviewers who are checking submissions to conferences and journals. In medicine and many other field of science, people can raise concerns about papers *after* they are published, and authors are expected to take this seriously. This is not the practice in NLP, which is a shame.
In our ReproHum project, we have found that many NLP experiments are flawed, and many authors do not respond to requests for more information about their work. This is depressing and hinders scientific progress in NLP.
I think there is a lot of potential in using chatGPT in healthcare, provided that we focus on real use cases instead of trying to debate whether chatGPT is somehow better than a doctor.
I love getting questions about how to evaluate chatGPT, they are much more constructive than speculations about whether it is a threat to humanity. We need to understand what LLM technology can and cannot do, and rigorous experiments are the best way to do this. I give some advice and caveats about evaluating chatGPT in this blog, and am happy to answer questions from people who want to do high-quality evaluations.
I dont like leaderboards, which encourage academics to write papers about small improvements on established tasks and datasets. I suspect (and hope) that chatGPT and similar systems will encourage people to move away from leaderboards. If so this would be great!
Ehud Reiter's Blog 