ReElicit uses LLMs to elicit adaptive feature embeddings for Gaussian process Bayesian optimization of system prompts under aggregate-only feedback, outperforming baselines across ten tasks with a 30-evaluation budget.
arXiv preprint arXiv:2306.03082 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Proposes compiling preference pairs into readable natural-language specifications for inference-time LLM alignment, claiming outperformance over DPO on dense-preference domains.
POES frames prompt evaluation as online adaptive testing and uses a provably submodular objective to pick informative examples, delivering 6.2% higher average accuracy and 35-60% token savings versus naive full-set scoring.
SPIRE approximates page-level slide personalization by training agents to denoise corrupted slide structures via collaborative RL, claiming a proof of consistency as a surrogate for inverse planning.
citing papers explorer
-
Embedding by Elicitation: Dynamic Representations for Bayesian Optimization of System Prompts
ReElicit uses LLMs to elicit adaptive feature embeddings for Gaussian process Bayesian optimization of system prompts under aggregate-only feedback, outperforming baselines across ten tasks with a 30-evaluation budget.
-
Towards Spec Learning: Inference-Time Alignment from Preference Pairs
Proposes compiling preference pairs into readable natural-language specifications for inference-time LLM alignment, claiming outperformance over DPO on dense-preference domains.
-
Select Smarter, Not More: Prompt-Aware Evaluation Scheduling with Submodular Guarantees
POES frames prompt evaluation as online adaptive testing and uses a provably submodular objective to pick informative examples, delivering 6.2% higher average accuracy and 35-60% token savings versus naive full-set scoring.
-
Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising
SPIRE approximates page-level slide personalization by training agents to denoise corrupted slide structures via collaborative RL, claiming a proof of consistency as a surrogate for inverse planning.