Fine-tuning shows higher proficiency than in-context learning on in-distribution generalization in formal languages, with equal out-of-distribution performance and diverging inductive biases at high proficiency.
Physics of language models: Part 1, context-free gram- mar
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
BERT learns shortcut solutions that impair generalization and forward transfer in continual LEGO, while ALBERT learns loop-like solutions for better performance, yet both fail at cross-experience composition, with ALBERT rescued by mixed-data training.
LLMs maintain surface syntax for novel CFGs but fail to preserve semantics under recursion and branching, relying on keyword bootstrapping rather than pure symbolic reasoning.
A 1.3B-parameter code model trained on 7B tokens of curated textbook and synthetic data achieves 50.6% on HumanEval, indicating data quality can enable strong performance at small scale.
citing papers explorer
-
Diagnosing CFG Interpretation in LLMs
LLMs maintain surface syntax for novel CFGs but fail to preserve semantics under recursion and branching, relying on keyword bootstrapping rather than pure symbolic reasoning.