2026-09-20T11:18:55Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/124428 2024-09-16 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

Chang, Kevin Chen-Chuan 2024-05 application/pdf en text Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms The student, Ziyi Chen, accepted the attached license on 2024-04-28 at 15:42. The student, Ziyi Chen, submitted this Thesis for approval on 2024-04-28 at 15:45. This Thesis was approved for publication on 2024-05-01 at 10:12. DSpace SAF Submission Ingestion Package generated from Vireo submission #20683 on 2024-09-16 at 00:37:20 Efficient retrieval-augmented generation Chen, Ziyi 2024-05-01 Efficient Natural Language Processing Retrieval-augmented Generation Retrieval-Augmented Generation (RAG) is a technique to augment language models with external knowledge of corpus. Despite the rapid evolution of large language models, RAG is still a promising method for solving the difficulty of updating information and unreliable memorization of large language models as many research endeavors and commercial services leveraged retrieval-augmented generation to improve reliability. However, RAG has its drawbacks including high latency and intensive computational resource utilization. The inefficiency resides in two aspects: the long input due to retrieved documents and slow autoregressive generation. To address these two issues, we propose Efficient Title Reranker, a fast reranker to select important documents for input, and Cascade Speculative Drafting which improves upon speculative decoding to increase the generation efficiency of large language models. The Efficient Title Reranker achieves state-of-the-art in retrieval accuracy while being more efficient than the baseline on the KILT knowledge benchmark. On the other hand, Cascade Speculative Drafting outperforms Speculative Decoding in generation speed on both GSM8k and MMLU without additional training. Text eng https://hdl.handle.net/2142/124428 Copyright 2024 Ziyi Chen M.S. Thesis Computer Science University of Illinois at Urbana-Champaign Computer Science