Loius (Look it up in the Structure): Benchmark and Techniques for Document structure aware LLM based Retrieval

Vineet Kumar, vishwajeet kumar, Jaydeep Sen, Riyaz Ahmad Bhat, Sachindra Joshi

Keywords: information retrieval, llm, model based retrieval, document search, retrieval benchmark, document structure, benchmark

TL;DR: Can we instruction finetune an LLM to pick the best subsection to answer a user query by showing it a Table of Contents of a long document?

Abstract:

We thank the reviewers for their valuable feedback. We have decided to withdraw the submission
from ICLR after careful consideration.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5983