Robert Kirk

5

Papers

399

Total Citations

1

Affiliations

Affiliations

University College London

Papers (5)

Understanding the Effects of RLHF on LLM Generalisation and Diversity

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

Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models

Investigating Non-Transitivity in LLM-as-a-Judge

Generalization to New Sequential Decision Making Tasks with In-Context Learning