Randomly replacing labels in in-context demonstrations barely hurts performance, showing that label space, input distribution, and sequence format drive in-context learning more than ground-truth labels.
Meta-learning via language model in-context tuning.ArXiv, abs/2110.07814
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
STaR-Quant provides a state-time consistent PTQ framework for DLLMs using SGAT and TAC to improve low-bit weight-activation quantization.
BinomMAML uses a binomial expansion to estimate meta-gradients more accurately than prior approximations, with error bounds that improve on existing methods and decay super-exponentially under mild conditions.
LLM system with LoRA fine-tuning and few-shot prompting wins reference-free financial misinformation detection task at 95.4% public and 96.3% private accuracy.
citing papers explorer
-
Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?
Randomly replacing labels in in-context demonstrations barely hurts performance, showing that label space, input distribution, and sequence format drive in-context learning more than ground-truth labels.
-
STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models
STaR-Quant provides a state-time consistent PTQ framework for DLLMs using SGAT and TAC to improve low-bit weight-activation quantization.
-
Binomial Gradient-Based Meta-Learning for Enhanced Meta-Gradient Estimation
BinomMAML uses a binomial expansion to estimate meta-gradients more accurately than prior approximations, with error bounds that improve on existing methods and decay super-exponentially under mild conditions.
-
Fact4ac at the Financial Misinformation Detection Challenge Task: Reference-Free Financial Misinformation Detection via Fine-Tuning and Few-Shot Prompting of Large Language Models
LLM system with LoRA fine-tuning and few-shot prompting wins reference-free financial misinformation detection task at 95.4% public and 96.3% private accuracy.