Task-preserving perturbations of correct exemplars can degrade ICL performance by changing the effective evidence mixture used for inference.
arXiv preprint arXiv:2302.11042 (2023)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Query position is a first-order variable in dLLM ICL whose variance matches semantic quality impact; mitigated via Average Confidence metric and training-free Auto-ICL routing.
DiSP stratifies queries by difficulty using random trial estimates, trains a router and level-specific judges, then applies budgeted stop-on-acceptance selection to improve ICL accuracy and speed on classification tasks.
citing papers explorer
-
When Correct Demonstrations Hurt: Rethinking the Role of Exemplars in In-Context Learning
Task-preserving perturbations of correct exemplars can degrade ICL performance by changing the effective evidence mixture used for inference.
-
Where to Place the Query? Unveiling and Mitigating Positional Bias in In-Context Learning for Diffusion LLMs via Decoding Dynamics
Query position is a first-order variable in dLLM ICL whose variance matches semantic quality impact; mitigated via Average Confidence metric and training-free Auto-ICL routing.
-
Easier to Judge than to Find: Predicting In-Context Learning Success for Demonstration Selection
DiSP stratifies queries by difficulty using random trial estimates, trains a router and level-specific judges, then applies budgeted stop-on-acceptance selection to improve ICL accuracy and speed on classification tasks.