We seek to create agents that both act and communicate with other agents in pursuit of a goal. Towards this end, we extend LIGHT (Urbanek et al. 2019)--a large-scale crowd …
CF Tsai, X Zhou, SS Liu, J Li, M Yu, H Mei - arXiv preprint arXiv …, 2023 - arxiv.org
Large language models (LLMs) such as ChatGPT and GPT-4 have recently demonstrated their remarkable abilities of communicating with human users. In this technical report, we …
J van Stegeren, J Myśliwiec - … of the 16th International Conference on the …, 2021 - dl.acm.org
GPT-2, a neural language model trained on a large dataset of English web text, has been used in a variety of natural language generation tasks because of the language quality and …
A hallmark of human intelligence is the ability to understand and communicate with language. Interactive Fiction games are fully text-based simulation environments where a …
To interact with humans in the world, agents need to understand the diverse types of language that people use, relate them to the visual world, and act based on them. While …
In this paper, we consider mimicking fictional characters as a promising direction for building engaging conversation models. To this end, we present a new practical task where only a …
The current mainstream approach to train natural language systems is to expose them to large amounts of text. This passive learning is problematic if we are interested in developing …
Models often easily learn biases present in the training data, and their predictions directly reflect this bias. We analyze gender bias in dialogue data, and examine how this bias is …
J Lee, K Cho, D Kiela - arXiv preprint arXiv:1909.04499, 2019 - arxiv.org
Emergent multi-agent communication protocols are very different from natural language and not easily interpretable by humans. We find that agents that were initially pretrained to …