works on
interpretability 1knowledge retrieval 1language model pretraining 1open-domain question answering 1retrieval-augmented models 1

From the 1 of 12 linked papers with an AI index.

activity
20162022
most citedREALM: Retrieval-Augmented Language Model Pre-Training

521 citations · 626 across the 9 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2018

Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration

Evan Zheran Liu, Kelvin Guu, Panupong Pasupat +2

Reinforcement learning (RL) agents improve through trial-and-error, but when reward is sparse and the agent cannot discover successful action sequences, learning stagnates. This ha…