TuringAdvice: A Generative and Dynamic Evaluation of Language Use
This work addresses the need for better evaluation of language understanding in AI, particularly for open-ended generative tasks, though it is incremental as it builds on existing datasets and models.
The authors tackled the problem of evaluating language understanding models by introducing TuringAdvice, a challenge task where models generate helpful advice for real-life situations, and found that even large models like T5 and GPT-3 perform poorly, with success rates of only 14% and 4% respectively.
We propose TuringAdvice, a new challenge task and dataset for language understanding models. Given a written situation that a real person is currently facing, a model must generate helpful advice in natural language. Our evaluation framework tests a fundamental aspect of human language understanding: our ability to use language to resolve open-ended situations by communicating with each other. Empirical results show that today's models struggle at TuringAdvice, even multibillion parameter models finetuned on 600k in-domain training examples. The best model, a finetuned T5, writes advice that is at least as helpful as human-written advice in only 14% of cases; a much larger non-finetunable GPT3 model does even worse at 4%. This low performance reveals language understanding errors that are hard to spot outside of a generative setting, showing much room for progress.