Papers › Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation

Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation

10 Apr 2024arXiv:2404.06910archive 2025-07-28

Thomas Merth, Qichen Fu, Mohammad Rastegari, Mahyar Najibi

Despite the successes of large language models (LLMs), they exhibit significant drawbacks, particularly when processing long contexts. Their inference cost scales quadratically with respect to sequence length, making it expensive for deployment in some real-world text processing applications, such as retrieval-augmented generation (RAG). Additionally, LLMs also exhibit the "distraction phenomenon", where irrelevant context in the prompt degrades output quality. To address these drawbacks, we propose a novel RAG prompting methodology, *superposition prompting*, which can be directly applied to pre-trained transformer-based LLMs *without the need for fine-tuning*. At a high level, superposition prompting allows the LLM to process input documents in parallel *prompt paths*, discarding paths once they are deemed irrelevant. We demonstrate the capability of our method to simultaneously enhance time efficiency across a variety of question-answering benchmarks using multiple pre-trained LLMs. Furthermore, our technique significantly improves accuracy when the retrieved context is large relative the context the model was trained on. For example, our approach facilitates a 93x reduction in compute time while *improving* accuracy by 43% on the NaturalQuestions-Open dataset with the MPT-7B instruction-tuned model over naive RAG.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

apple/ml-superposition-prompting officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Question Answering RAG Retrieval Retrieval-augmented Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Adam Attention Attention Dropout BART BERT BPE Dense Connections Dropout Layer Normalization Linear Layer Linear Warmup With Linear Decay Multi-Head Attention RAG Residual Connection Softmax Weight Decay WordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections