Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure

摘要

Despite their impressive capabilities, LLMs exhibit a basic generalization failure known as the *Reversal Curse*, where they struggle to learn reversible factual associations. Understanding why this occurs could help identify weaknesses in current models and advance their generalization and robustness. In this paper, we conjecture that the Reversal Curse in LLMs is a manifestation of the long-standing *binding problem* in cognitive science, neuroscience and AI. Specifically, we hypothesize two primary causes of the Reversal Curse stemming from transformers' limitations in conceptual binding: the *inconsistency* and *entanglements* of concept representations. We perform a series of experiments that support these conjectures. Our exploration leads to a model design based on JEPA (Joint-Embedding Predictive Architecture) that for the first time breaks the Reversal Curse without side-stepping it with specialized data augmentation or non-causal masking, and moreover, generalization could be further improved by incorporating special memory layers that support disentangled concept representations. Our research opens up the broader fundamental challenge of designing models capable of learning systematic conceptual binding with less human scaffolding.