← Search

Nader Akoury

2 accepted papers

2023

A Framework for Exploring Player Perceptions of LLM-Generated Dialogue in Commercial Video Games

EMNLP 2023long findings

The growing capabilities of large language models (LLMs) have inspired recent efforts to integrate LLM-generated dialogue into video games. However, evaluation remains a major challenge: how do we assess the player experience in a commercial game augmented with LLM-generated dialogue? To explore thi…

Cited by 0SourceScholar
2021

The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation

EMNLP 2021main

Recent text generation research has increasingly focused on open-ended domains such as story and poetry generation. Because models built for such tasks are difficult to evaluate automatically, most researchers in the space justify their modeling choices by collecting crowdsourced human judgments of…

Cited by 136SourcePDFScholar