To produce accurate predictions, language models (LMs) must balance between generalization and memorization. Yet, little is known about the mechanism by which transformer LMs employ their memorization capacity. When does a model decide to output a memorized phrase, and how is this phrase then retrieved from memory? In this work, we offer the first methodological framework for probing and characterizing recall of memorized sequences in transformer LMs. First, we lay out criteria for detecting model inputs that trigger memory recall, and propose idioms as inputs that typically fulfill these criteria. Next, we construct a dataset of English idioms and use it to compare model behavior on memorized vs. non-memorized inputs. Specifically, we analyze the internal prediction construction process by interpreting the model’s hidden representations as a gradual refinement of the output probability distribution. We find that across different model sizes and architectures, memorized predictions are a two-step process: early layers promote the predicted token to the top of the output distribution, and upper layers increase model confidence. This suggests that memorized information is stored and retrieved in the early layers of the network. Last, we demonstrate the utility of our methodology beyond idioms in memorized factual statements. Overall, our work makes a first step towards understanding memory recall, and provides a methodological basis for future studies of transformer memorization.

Feed-forward layers constitute two-thirds of a transformer model’s parameters, yet their role in the network remains under-explored. We show that feed-forward layers in transformer-based language models operate as key-value memories, where each key correlates with textual patterns in the training examples, and each value induces a distribution over the output vocabulary. Our experiments show that the learned patterns are human-interpretable, and that lower layers tend to capture shallow patterns, while upper layers learn more semantic ones. The values complement the keys’ input patterns by inducing output distributions that concentrate probability mass on tokens likely to appear immediately after each pattern, particularly in the upper layers. Finally, we demonstrate that the output of a feed-forward layer is a composition of its memories, which is subsequently refined throughout the model’s layers via residual connections to produce the final output distribution.

Recent developments in neural language models (LMs) have raised concerns about their potential misuse for automatically spreading misinformation. In light of these concerns, several studies have proposed to detect machine-generated fake news by capturing their stylistic differences from human-written text. These approaches, broadly termed stylometry, have found success in source attribution and misinformation detection in human-written texts. However, in this work, we show that stylometry is limited against machine-generated misinformation. Whereas humans speak differently when trying to deceive, LMs generate stylistically consistent text, regardless of underlying motive. Thus, though stylometry can successfully prevent impersonation by identifying text provenance, it fails to distinguish legitimate LM applications from those that introduce false information. We create two benchmarks demonstrating the stylistic similarity between malicious and legitimate uses of LMs, utilized in auto-completion and editing-assistance settings.1 Our findings highlight the need for non-stylometry approaches in detecting machine-generated misinformation, and open up the discussion on the desired evaluation benchmarks.