A test-time zeroth-order optimization of prompt embeddings using a bounded self-supervised proxy from demonstration log-probabilities improves ICL accuracy and correlates with gains across tasks.
Self-generated in-context learning: Leveraging auto-regressive language models as a demonstration generator
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Echo framework enables experience transfer for multimodal LLM agents in Minecraft by decomposing knowledge into structure, attribute, process, function, and interaction dimensions and applying in-context analogy learning, achieving 1.3x-1.7x speedup on object-unlocking tasks with burst-like chain-un
PICCO is a five-element reference architecture (Persona, Instructions, Context, Constraints, Output) for structuring LLM prompts, derived from synthesizing prior frameworks along with a taxonomy distinguishing prompt concepts.
A survey categorizing scaling in LLM reasoning across input size, steps, rounds, training, and future directions, noting that scaling can negatively affect performance.
citing papers explorer
-
Self-Improving In-Context Learning
A test-time zeroth-order optimization of prompt embeddings using a bounded self-supervised proxy from demonstration log-probabilities improves ICL accuracy and correlates with gains across tasks.
-
Experience Transfer for Multimodal LLM Agents in Minecraft Game
Echo framework enables experience transfer for multimodal LLM agents in Minecraft by decomposing knowledge into structure, attribute, process, function, and interaction dimensions and applying in-context analogy learning, achieving 1.3x-1.7x speedup on object-unlocking tasks with burst-like chain-un
-
The PICCO Framework for Large Language Model Prompting: A Taxonomy and Reference Architecture for Prompt Structure
PICCO is a five-element reference architecture (Persona, Instructions, Context, Constraints, Output) for structuring LLM prompts, derived from synthesizing prior frameworks along with a taxonomy distinguishing prompt concepts.
-
A Survey of Scaling in Large Language Model Reasoning
A survey categorizing scaling in LLM reasoning across input size, steps, rounds, training, and future directions, noting that scaling can negatively affect performance.