The dissertation shows that text-centric prompting, inference-time optimization, and correct-by-construction synthetic data can improve LLM robustness and Verilog code generation under resource constraints.
Benchmarking Large Language Model Uncertainty for Prompt Optimization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Prompt optimization algorithms for Large Language Models (LLMs) excel in multi-step reasoning but still lack effective uncertainty estimation. This paper introduces a benchmark dataset to evaluate uncertainty metrics, focusing on Answer, Correctness, Aleatoric, and Epistemic Uncertainty. Through analysis of models like GPT-3.5-Turbo and Meta-Llama-3.1-8B-Instruct, we show that current metrics align more with Answer Uncertainty, which reflects output confidence and diversity, rather than Correctness Uncertainty, highlighting the need for improved metrics that are optimization-objective-aware to better guide prompt optimization. Our code and dataset are available at https://github.com/0Frett/PO-Uncertainty-Benchmarking.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Generalizing Large Language Model Usability Across Resource-Constrained
The dissertation shows that text-centric prompting, inference-time optimization, and correct-by-construction synthetic data can improve LLM robustness and Verilog code generation under resource constraints.