Deployed software systems need to be maintained as bugs emerge and the domain and user needs evolve; this perhaps is especially challenging for systems based on LLMs. Unfortunately little is known about maintaining NLG systems,
In NLG we focus on quantitative evaluation, but qualitative techniques can also be used. Quantatitive hypothesis testing is essential, but its also really useful to ask people what they think of an NLG system in an open-ended way.
The UK government wants to reform the UK health system by digitisation, shifting care to communities, and focusing on prevention. I think there is a lot of potential for AI to help with this, if AI/Medicine researchers become less fixated on using AI to improve diagnoses in hospitals.
In early Sept I ran a one-day class on evaluation. I summarise what I did in this class and give links to my presentations, in case this is useful to other people.
Sometimes the latest technology is *not* appropriate for an NLG task. I saw this very strongly in the late 2010s with LSTMs (which do not work well for data-to-text), and continue to see this in 2024 (GPT4 is not always the best approach). Both researchers and developers need to be open-minded about alternative approaches.
I’m now part-way towards retirement, and working fewer hours (for less money) while have more time for trips and other personal activities. A few people have asked about this, so I thought I’d explain in a blog.
AI has many promising applications in healthcare, but adoption of AI in healthcare is very slow. One message from a recent workshop I attended is that it would help if AI researchers had a better understanding of requirements of the health sector, including evaluation, challenges, and business cases.
I list five challenges to evaluating LLMs, which unfortunately seem to be ignored by many researchers. Which means that many published LLM evaluations cannot be trusted. This blog is based on a recent workshop talk.
This is a personal blog about a recent bike trip I did from Perth (Scotland) to Preston (England).
I suspect we may be reaching the point where the most common type of human evaluation in NLG (ratings/rankings by crowdworkers or students) are less meaningful than evaluations using LLMs. But better forms of human evaluation, based on annotation or impact, are still very useful and give insights which we cannot get from LLMs.
