A controlled formal language task reveals fine-tuning outperforms in-context learning on in-distribution generalization but equals it on out-of-distribution, with ICL showing greater sensitivity to model size and tokenization.
Few-shot fine-tuning vs
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
An adaptive test-time framework uses a warm-up phase on the test set to build evolving in-context examples, then concentrates compute on unresolved queries to outperform static baselines on math, coding, and reasoning tasks with lower total inference cost.
citing papers explorer
-
Fine-tuning vs. In-context Learning in Large Language Models: A Formal Language Learning Perspective
A controlled formal language task reveals fine-tuning outperforms in-context learning on in-distribution generalization but equals it on out-of-distribution, with ICL showing greater sensitivity to model size and tokenization.
-
Adaptive Test-Time Compute Allocation with Evolving In-Context Demonstrations
An adaptive test-time framework uses a warm-up phase on the test set to build evolving in-context examples, then concentrates compute on unresolved queries to outperform static baselines on math, coding, and reasoning tasks with lower total inference cost.
- Mitigating Cross-Lingual Cultural Inconsistencies in LLMs via Consensus-Driven Preference Optimisation