Edward Grefenstette

papers

1,141

total citations

papers (11)

Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks

ICLR 2024arXiv

citations

Improving Intrinsic Exploration with Language Abstractions

NEURIPS 2022arXiv

citations

The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs

NEURIPS 2023arXiv

citations

Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models

ICLR 2025arXiv

citations

Grounding Aleatoric Uncertainty for Unsupervised Environment Design

NEURIPS 2022arXiv

citations

Improving Policy Learning via Language Dynamics Distillation

NEURIPS 2022arXiv

citations

Learning General World Models in a Handful of Reward-Free Deployments

NEURIPS 2022arXiv

citations

Edward Grefenstette

papers (11)

Understanding the Effects of RLHF on LLM Generalisation and Diversity

Debating with More Persuasive LLMs Leads to More Truthful Answers

The NetHack Learning Environment

Replay-Guided Adversarial Environment Design

Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks

Improving Intrinsic Exploration with Language Abstractions

The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs

Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models

Grounding Aleatoric Uncertainty for Unsupervised Environment Design

Improving Policy Learning via Language Dynamics Distillation

Learning General World Models in a Handful of Reward-Free Deployments

papers (11)

Understanding the Effects of RLHF on LLM Generalisation and Diversity

Debating with More Persuasive LLMs Leads to More Truthful Answers

The NetHack Learning Environment

Replay-Guided Adversarial Environment Design

Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks

Improving Intrinsic Exploration with Language Abstractions

The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs

Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models

Grounding Aleatoric Uncertainty for Unsupervised Environment Design

Improving Policy Learning via Language Dynamics Distillation

Learning General World Models in a Handful of Reward-Free Deployments