3 accepted papers
Chess has long been a testbed for AI's quest to match human intelligence, and in recent years, chess AI systems have surpassed the strongest humans at the game. However, these systems are *not human-aligned*; they are unable to match the skill levels of all human partners or model human-like behavio…
We address a fundamental challenge in Natural Language Generation (NLG) model evaluation---the design and evaluation of evaluation metrics. Recognizing the limitations of existing automatic metrics and noises from how current human evaluation was conducted, we propose MetricEval, a framework informe…
Automatic summarization methods are efficient but can suffer from low quality. In comparison, manual summarization is expensive but produces higher quality. Can humans and AI collaborate to improve summarization performance? In similar text generation tasks (e.g., machine translation), human-AI coll…