SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.09801 · EMNLP · 2024

EFUF: Efficient Fine-Grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models

Zhen Wu, Xinyu Dai, Fei Zhao, Jianbing Zhang, Chunhui Li, Shangyu Xing, Tuo An, Weihao Chen

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 1 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2402.09801.json · badge: /api/ran/2402.09801.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
starreeze/efuf canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
FunctionStatusWhere it lives
bloom_forward Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
starreeze/efuf/Owl/mplug_owl/modeling_mplug_owl.py
pointer only (licence: GPL-3.0) · get_code("1a531e3c0d1094fb")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, starreeze/efuf, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_ltor_masks_and_position_ids_from_embeddings Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
starreeze/efuf/Owl/mplug_owl/modeling_mplug_owl.py
pointer only (licence: GPL-3.0) · get_code("45567e61fe09093a")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, starreeze/efuf, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_media_indices Ran
ran; our contract draft was wrong, not the code
starreeze/efuf/Owl/mplug_owl/modeling_mplug_owl.py
pointer only (licence: GPL-3.0) · get_code("265f4d55ccd60d18")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, starreeze/efuf, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_media_types Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
starreeze/efuf/Owl/mplug_owl_video/modeling_mplug_owl.py
pointer only (licence: GPL-3.0) · get_code("752b84a6f01c43d8")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, starreeze/efuf, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

post_process_code Ran
ran; our contract draft was wrong, not the code
starreeze/efuf/Owl/serve/model_utils.py
pointer only (licence: GPL-3.0) · get_code("15e54d5d53ab90ac")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, starreeze/efuf, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

post_process_output Ran
ran; our contract draft was wrong, not the code
starreeze/efuf/Owl/serve/model_utils.py
pointer only (licence: GPL-3.0) · get_code("607a861da4671ce5")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, starreeze/efuf, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

gpt_infer Not yet run
unverified (harvested, no recorded run)
starreeze/efuf/common/gpt.py
pointer only (licence: GPL-3.0) · get_code("a12935f8894cc5de")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, starreeze/efuf, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 6 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 2 the same month, 6 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_ltor_masks_and_position_ids_from_embeddings 7 other papers
4 dated earlier, 3 later
2023.findings-emnlp.187 (2023 (year only))
UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model
2302.00402 (2023-02)
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
2308.06595 (2023-08)
VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use
and 4 more not named here
get_media_indices 6 other papers
3 dated earlier, 3 later
2302.00402 (2023-02)
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
2308.06595 (2023-08)
VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use
2312.06742 (2023-12)
Honeybee: Locality-enhanced Projector for Multimodal LLM
and 3 more not named here
post_process_code 5 other papers
3 dated earlier, 1 the same month, 1 later
2023.findings-emnlp.187 (2023 (year only))
UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model
2310.05126 (2023-10)
UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model
2312.06742 (2023-12)
Honeybee: Locality-enhanced Projector for Multimodal LLM
and 2 more not named here
post_process_output 5 other papers
3 dated earlier, 1 the same month, 1 later
2023.findings-emnlp.187 (2023 (year only))
UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model
2310.05126 (2023-10)
UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model
2312.06742 (2023-12)
Honeybee: Locality-enhanced Projector for Multimodal LLM
and 2 more not named here
bloom_forward 2 other papers
1 dated earlier, 1 later
2308.06595 (2023-08)
VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use
2403.07350 (2024-03)
VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark
get_media_types 2 other papers
2 later
2403.07350 (2024-03)
VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark
2503.06800 (2025-03)
VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Multimodal large language models (MLLMs) have attracted increasing attention in the past few years, but they may still generate descriptions that include objects not present in the corresponding images, a phenomenon known as object hallucination. To eliminate hallucinations, existing methods manually annotate paired responses with and without hallucinations, and then employ various alignment algorithms to improve the alignment capability between images and text. However, they not only demand considerable computation resources during the finetuning stage but also require expensive human annotation to construct paired data needed by the alignment algorithms. To address these issues, we propose an efficient fine-grained unlearning framework (EFUF), which performs gradient ascent utilizing three tailored losses to eliminate hallucinations without paired data. Extensive experiments show that our method consistently reduces hallucinations while preserving the generation quality with modest computational overhead. Our code and datasets are available at https://github.com/starreeze/efuf.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.09801")
get_code_for_paper("2402.09801")
have("2402.09801")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.09801.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.09801.svg)](https://syntology.ai/paper/2402.09801)

Connect an agent — have() is free.