M-Ped: Multi-Prompt Ensemble Decoding for Large Language Models
This addresses performance enhancement for LLMs in NLP applications, representing an incremental improvement over existing methods.
The paper tackles the problem of improving large language model (LLM) generation quality by introducing a multi-prompt ensemble decoding approach, which aggregates outputs from multiple prompt variations to achieve substantial gains in BLEU scores, pass@k rates, and LENS metrics across tasks like machine translation and code generation.
With the widespread application of Large Language Models (LLMs) in the field of Natural Language Processing (NLP), enhancing their performance has become a research hotspot. This paper presents a novel multi-prompt ensemble decoding approach designed to bolster the generation quality of LLMs by leveraging the aggregation of outcomes from multiple prompts. Given a unique input $X$, we submit $n$ variations of prompts with $X$ to LLMs in batch mode to decode and derive probability distributions. For each token prediction, we calculate the ensemble probability by averaging the $n$ probability distributions within the batch, utilizing this aggregated probability to generate the token. This technique is dubbed Inner-Batch Ensemble. To facilitate efficient batch inference, we implement a Left-Padding strategy to maintain uniform input lengths across the n prompts. Through extensive experimentation on diverse NLP tasks, including machine translation, code generation, and text simplification, we demonstrate the efficacy of our method in enhancing LLM performance. The results show substantial improvements in BLEU scores, pass@$k$ rates, and LENS metrics over conventional methods.