2025
Fact Recall, Heuristics or Pure Guesswork? Precise Interpretations of Language Models for Fact Completion
ACL 2025finding
Language models (LMs) can make a correct prediction based on many possible signals in a prompt, not all corresponding to recall of factual associations. However, current interpretations of LMs fail to take this into account. For example, given the query “Astrid Lindgren was born in” with the corresp…