Papers › LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for...

LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression Comprehension

18 Sep 2024arXiv:2409.11919archive 2025-07-28

Amaia Cardiel, Eloi Zablocki, Elias Ramzi, Oriane Siméoni, Matthieu Cord

Vision Language Models (VLMs) have demonstrated remarkable capabilities in various open-vocabulary tasks, yet their zero-shot performance lags behind task-specific finetuned models, particularly in complex tasks like Referring Expression Comprehension (REC). Fine-tuning usually requires 'white-box' access to the model's architecture and weights, which is not always feasible due to proprietary or privacy concerns. In this work, we propose LLM-wrapper, a method for 'black-box' adaptation of VLMs for the REC task using Large Language Models (LLMs). LLM-wrapper capitalizes on the reasoning abilities of LLMs, improved with a light fine-tuning, to select the most relevant bounding box matching the referring expression, from candidates generated by a zero-shot black-box VLM. Our approach offers several advantages: it enables the adaptation of closed-source models without needing access to their internal workings, it is versatile as it works with any VLM, it transfers to new VLMs, and it allows for the adaptation of an ensemble of VLMs. We evaluate LLM-wrapper on multiple datasets using different VLMs and LLMs, demonstrating significant performance improvements and highlighting the versatility of our method. While LLM-wrapper is not meant to directly compete with standard white-box fine-tuning, it offers a practical and effective alternative for black-box VLM adaptation. The code will be open-sourced.

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="2409.11919")

Code

Syntology Ran 9 of 18 code samples harvested from 1 repository linked to this paper; 9 have no recorded run. Of those that ran: 1 ran · honoured contract; 4 ran · our draft was wrong; 1 ran · fixture could not drive it; 3 ran with no contract checked.

By repository: official repository: 18 samples from 1 repository, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

valeoai/LLM_wrapper 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

18 samples harvested; 9 ran; 1 honoured the contract we drafted; 9 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.

1ran · honoured contract
4ran · our draft was wrong
1ran · fixture could not drive it
3ran
9unverified

Licence: 0 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 valeoai/LLM_wrapper. “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.

convert_box_coord_list valeoai/LLM_wrapper/llm_wrapper/LLM_inference_script.py official repository ran · fixture could not drive it MIT (permissive) · 496f36883982907e · report
create_my_prompt valeoai/llm_wrapper/llm_wrapper/LLM_finetuning_script.py official repository ran · our draft was wrong MIT (permissive) · b62369eaf6443bf1 · report
define_modules_to_FT valeoai/llm_wrapper/llm_wrapper/LLM_finetuning_script.py official repository ran · our draft was wrong MIT (permissive) · f96ceeee851477a5 · report
define_short_LLM_folder_name valeoai/LLM_wrapper/llm_wrapper/LLM_inference_script.py official repository ran MIT (permissive) · d1d34bdea6597b80 · report
eval_post_step_3 valeoai/LLM_wrapper/llm_wrapper/LLM_inference_script.py official repository ran MIT (permissive) · 6921e7c0cacc7dc8 · report
extract_int_result_from_LLM_gen valeoai/LLM_wrapper/llm_wrapper/LLM_inference_script.py official repository ran fingerprinted MIT (permissive) · ff499b564cc9cdab · report
get_HF_model_id valeoai/LLM_wrapper/llm_wrapper/LLM_inference_script.py official repository ran · our draft was wrong MIT (permissive) · 0262028d2a06ec2b · report
get_all_rec_and_thres_boxes_concat valeoai/llm_wrapper/llm_wrapper/LLM_inference_script.py official repository ran · honoured contract MIT (permissive) · 8e0fab2c4512a48c · report
get_box_key_list valeoai/llm_wrapper/llm_wrapper/LLM_inference_script.py official repository ran · our draft was wrong MIT (permissive) · d4ea0c52a00729fd · report
REC_eval_step valeoai/LLM_wrapper/llm_wrapper/LLM_inference_script.py official repository unverified MIT (permissive) · 9b28e2f8ef578805 · report
compute_and_save_infer_info valeoai/LLM_wrapper/llm_wrapper/LLM_inference_script.py official repository unverified MIT (permissive) · d8cd5bf64f19e875 · report
define_model_result_name valeoai/LLM_wrapper/llm_wrapper/LLM_inference_script.py official repository unverified MIT (permissive) · 9c81b8cf59bd8a8f · report
design_prompt_for_step_3 valeoai/LLM_wrapper/llm_wrapper/LLM_inference_script.py official repository unverified MIT (permissive) · b2acae0f31bbf97f · report
gen_step_3_with_HF valeoai/LLM_wrapper/llm_wrapper/LLM_inference_script.py official repository unverified MIT (permissive) · 1ee6940816fb4c9c · report
get_all_rec_and_thres_dict_info_concat valeoai/LLM_wrapper/llm_wrapper/LLM_inference_script.py official repository unverified MIT (permissive) · 14a0b26b9f4d5f93 · report
load_FT_model_via_base_model valeoai/LLM_wrapper/llm_wrapper/LLM_inference_script.py official repository unverified MIT (permissive) · 60c7a23e50408bb4 · report
load_HF_model_tok valeoai/LLM_wrapper/llm_wrapper/LLM_inference_script.py official repository unverified MIT (permissive) · 69336c48b701b32e · report
unify_output_step_3 valeoai/LLM_wrapper/llm_wrapper/LLM_inference_script.py official repository unverified MIT (permissive) · 10a0bb17e5386ba9 · report

Tasks

Referring ExpressionReferring Expression Comprehension

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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