Papers › SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Information

SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Information

21 Sep 2024arXiv:2409.14083archive 2025-07-28

Jiashuo Sun, Jihai Zhang, Yucheng Zhou, Zhaochen Su, Xiaoye Qu, Yu Cheng

Large Vision-Language Models (LVLMs) have become pivotal at the intersection of computer vision and natural language processing. However, the full potential of LVLMs Retrieval-Augmented Generation (RAG) capabilities remains underutilized. Existing works either focus solely on the text modality or are limited to specific tasks. Moreover, most LVLMs struggle to selectively utilize retrieved information and are sensitive to irrelevant or misleading references. To address these challenges, we propose a self-refinement framework designed to teach LVLMs to Selectively Utilize Retrieved Information (SURf). Specifically, when given questions that are incorrectly answered by the LVLM backbone, we obtain references that help correct the answers (positive references) and those that do not (negative references). We then fine-tune the LVLM backbone using a combination of these positive and negative references. Our experiments across three tasks and seven datasets demonstrate that our framework significantly enhances LVLMs ability to effectively utilize retrieved multimodal references and improves their robustness against irrelevant or misleading information. The source code is available at https://github.com/GasolSun36/SURf.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2409.14083")

Code

Syntology Ran 18 of 18 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 1 ran · fixture could not drive it; 15 ran with no contract checked.

By repository: official repository: 18 samples from 1 repository, 18 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

gasolsun36/surf officialmentioned in papermentioned 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

18 samples harvested; 18 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
1ran · fixture could not drive it
15ran

Licence: 18 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from GasolSun36/SURf. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

build_prompt GasolSun36/SURf/eval/pope.py official repository ran fingerprinted no licence file found · pointer only · c8c51dd88ad58cb1 · report
build_prompt GasolSun36/SURf/initial/data_filter.py official repository ran fingerprinted no licence file found · pointer only · 48f2a9620f2ac197 · report
calculate_metrics GasolSun36/SURf/eval/eval_pope.py official repository ran no licence file found · pointer only · 31fd3eb13a63be04 · report
compute_statistics GasolSun36/SURf/eval/eval_pope.py official repository ran no licence file found · pointer only · f63fb039437be784 · report
create_faiss_index GasolSun36/SURf/database/create_index.py official repository ran no licence file found · pointer only · 4267a0b07402b7e7 · report
divide_to_patches GasolSun36/SURf/llava/mm_utils.py official repository ran no licence file found · pointer only · 7e03b180fa317c9a · report
exact_match GasolSun36/SURf/initial/tool_evaluate.py official repository ran fingerprinted no licence file found · pointer only · 442f044af42b5b3f · report
generate_clip_vectors GasolSun36/SURf/database/create_index.py official repository ran no licence file found · pointer only · 94855420b055f5cb · report
get_chunk GasolSun36/SURf/initial/generate_initial_data.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 42a46570620cd9fa · report
get_chunk GasolSun36/SURf/eval/pope.py official repository ran fingerprinted no licence file found · pointer only · 06d40f4711e62357 · report
get_chunk gasolsun36/surf/initial/tool_evaluate.py official repository ran fingerprinted no licence file found · pointer only · 8a203abf91abfcad · report
load_faiss_index GasolSun36/SURf/eval/pope.py official repository ran no licence file found · pointer only · c440a6c78fc9fc04 · report
load_files GasolSun36/SURf/eval/eval_pope.py official repository ran no licence file found · pointer only · 1bdb9a6725f61c1d · report
resize_and_pad_image GasolSun36/SURf/llava/mm_utils.py official repository ran no licence file found · pointer only · 468eedeba67f1b00 · report
retrieve_base_filenames GasolSun36/SURf/initial/data_filter.py official repository ran no licence file found · pointer only · e6cc6a9ac7adfd83 · report
select_best_resolution GasolSun36/SURf/llava/mm_utils.py official repository ran · fixture could not drive it no licence file found · pointer only · 3999ff487573f32c · report
split_list GasolSun36/SURf/initial/generate_initial_data.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 076c252c52cbb161 · report
split_list gasolsun36/surf/initial/tool_evaluate.py official repository ran fingerprinted no licence file found · pointer only · abe4f5d245fa207a · report

Tasks

RAGRetrieval-augmented Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

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