activity
20162026
most citedRELIC: Investigating Large Language Model Responses using Self-Consistency

33 citations · 233 across the 109 of their papers we have counts for

collaborators
Showing 2021Show all

9 papers · 1 filter

cs.CL2021

Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP

Zhijing Jin, Julius von Kügelgen, Jingwei Ni +4

The principle of independent causal mechanisms (ICM) states that generative processes of real world data consist of independent modules which do not influence or inform each other.…

cs.CL2021

Case-based Reasoning for Better Generalization in Textual Reinforcement Learning

Mattia Atzeni, Shehzaad Dhuliawala, Keerthiram Murugesan +1

Text-based games (TBG) have emerged as promising environments for driving research in grounded language understanding and studying problems like generalization and sample efficienc…

cs.LG2021

On Learning the Transformer Kernel

Sankalan Pal Chowdhury, Adamos Solomou, Avinava Dubey +1

In this work we introduce KERNELIZED TRANSFORMER, a generic, scalable, data driven framework for learning the kernel function in Transformers. Our framework approximates the Transf…

cs.CL2021★ 4 cited

"Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding

Faeze Brahman, Meng Huang, Oyvind Tafjord +3

When reading a literary piece, readers often make inferences about various characters' roles, personalities, relationships, intents, actions, etc. While humans can readily draw upo…

cs.CL2021

Differentiable Subset Pruning of Transformer Heads

Jiaoda Li, Ryan Cotterell, Mrinmaya Sachan

Multi-head attention, a collection of several attention mechanisms that independently attend to different parts of the input, is the key ingredient in the Transformer. Recent work…

cs.CL2021

Self-Supervised Contrastive Learning with Adversarial Perturbations for Defending Word Substitution-based Attacks

Zhao Meng, Yihan Dong, Mrinmaya Sachan +1

In this paper, we present an approach to improve the robustness of BERT language models against word substitution-based adversarial attacks by leveraging adversarial perturbations…