2026-09-20T11:11:11Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/129301 2025-10-20 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

application/pdf en text Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms The student, Xiaocong Yang, accepted the attached license on 2025-05-01 at 17:14. The student, Xiaocong Yang, submitted this Thesis for approval on 2025-05-01 at 17:21. This Thesis was approved for publication on 2025-05-08 at 11:20. DSpace SAF Submission Ingestion Package generated from Vireo submission #22161 on 2025-10-19 at 18:11:30 LLM2IR: simple unsupervised contrastive learning makes long-context LLM great retriever Yang, Xiaocong 2025-05-08 Zhai, Chengxiang Information Retrieval Large Language Models eng Modern dense information retrieval (IR) models usually rely on costly large-scale pretraining. In this paper, we introduce LLM2IR, an efficient unsupervised contrastive learning framework to convert any decoder-only large language model (LLM) to an information retrieval model. Despite its simplicity, the effectiveness is proven among different LLMs on multiple IR benchmarks including LoCo, LongEmbed and BEIR. We also find that models with a longer context length tend to have a stronger IR capacity by comparing task performances of models in the same model family. Our work not only provides an effective way to build IR models on the state-of-the-art LLMs, but also shed light on the relationship between information retrieval ability and model context length, which helps the design of better information retrievers. 2025-05 Text https://hdl.handle.net/2142/129301 Copyright 2025 Xiaocong Yang Siebel School Comp & Data Sci Computer Science University of Illinois Urbana-Champaign M.S. Thesis