activity
20162025
most citedBeyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

565 citations · 814 across the 35 of their papers we have counts for

collaborators
Showing 2022Show all

8 papers · 1 filter

cs.CL2022★ 3 cited

SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization

Hyunwoo Kim, Jack Hessel, Liwei Jiang +9

Data scarcity has been a long standing issue in the field of open-domain social dialogue. To quench this thirst, we present SODA: the first publicly available, million-scale high-q…

cs.CL2022★ 11 cited

Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs

Maarten Sap, Ronan LeBras, Daniel Fried +1

Social intelligence and Theory of Mind (ToM), i.e., the ability to reason about the different mental states, intents, and reactions of all people involved, allow humans to effectiv…

cs.CL2022★ 565 cited

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao +448

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabil…

cs.CL2022★ 18 cited

Multimodal Knowledge Alignment with Reinforcement Learning

Youngjae Yu, Jiwan Chung, Heeseung Yun +8

Large language models readily adapt to novel settings, even without task-specific training data. Can their zero-shot capacity be extended to multimodal inputs? In this work, we pro…

cs.CL2022★ 8 cited

Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations

Jaehun Jung, Lianhui Qin, Sean Welleck +4

Despite their impressive capabilities, large pre-trained language models (LMs) struggle with consistent reasoning; recently, prompting LMs to generate explanations that self-guide…

cs.CL2022

Twist Decoding: Diverse Generators Guide Each Other

Jungo Kasai, Keisuke Sakaguchi, Ronan Le Bras +5

Many language generation models are now available for a wide range of generation tasks, including machine translation and summarization. Combining such diverse models may lead to f…