The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"

NeurIPS 2023 Workshop ICBINB Submission7 Authors

Published: 27 Oct 2023, Last Modified: 01 Dec 2023ICBINB 2023EveryoneRevisionsBibTeX
Keywords: LLMs, Large Language Models, Question Answering, Generalization, Knowledge Representation, Logical Inference, Relations
TL;DR: We demonstrate experimentally that LLMs trained on facts in one direction ("A is B") do not generalize to the reverse direction ("B is A").
Abstract: We expose a surprising failure of generalization in auto-regressive large language models (LLMs). If a model is trained on a sentence of the form "*A is B*", it will not automatically generalize to the reverse direction "*B is A*". This is the **Reversal Curse**. For instance, if a model is trained on "Olaf Scholz was the ninth Chancellor of Germany", it will not automatically be able to answer the question, "Who was the ninth Chancellor of Germany?". Moreover, the likelihood of the correct answer ("Olaf Scholz") will not be higher than for a random name. Thus, models exhibit a basic failure of logical deduction and do not generalize a prevalent pattern in their training set (i.e. if "*A is B*" occurs, "*B is A*" is more likely to occur). We provide evidence for the Reversal Curse by finetuning GPT-3 and Llama-1 on fictitious statements such as "Uriah Hawthorne is the composer of *Abyssal Melodies*" and showing that they fail to correctly answer "Who composed *Abyssal Melodies?*". The Reversal Curse is robust across model sizes and model families and is not alleviated by data augmentation. We also evaluate ChatGPT (GPT-3.5 and GPT-4) on questions about real-world celebrities, such as "Who is Tom Cruise's mother? [A: Mary Lee Pfeiffer]" and the reverse "Who is Mary Lee Pfeiffer's son?". GPT-4 correctly answers questions like the former 79% of the time, compared to 33% for the latter. This shows a failure of logical deduction that we hypothesize is caused by the Reversal Curse.
Submission Number: 7
Loading