SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.15316 · 2026

The Paradigm Shift: A Comprehensive Survey on Large Vision Language Models for Multimodal Fake News Detection

Tao Meng, Wei Ai, Yuntao Shou, Haowen Chen, Keqin Li, Yilong Tan, Zhixiong He

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 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; 3 failures of our instrument; 2 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/2601.15316.json · badge: /api/ran/2601.15316.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
majingCUHK/Rumor_RvNN canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
FunctionStatusWhere it lives
evaluation_2class Ran
ran; our contract draft was wrong, not the code
majingCUHK/Rumor_RvNN/model/evaluate.py
code served (permissive licence) · get_code("9257cea1dc609719")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# The function expects:
# - prediction: a list of items where prediction[i][0] is a list-like of 2 values
# - y: a list of items where y[i] is a list-like of 2 values with exactly one max

# Create prediction: list of 2 samples, each with shape [1, 2] (scores for 2 classes)
prediction = [
    [[0.1, 0.9]],  # sample 1: predictions for class 1 and class 2
    [[0.8, 0.2]]   # sample 2: predictions for class 1 and class 2
]

# Create y: list of 2 samples, each with 2 one-hot encoded values
# For 2-class classification, one value should be max
y = [
    [0, 1],  # sample 1: true class is 2 (index 1)
    [1, 0]   # sample 2: true class is 1 (index 0)
]

ARGS = {
    "prediction": prediction,
    "y": y
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
gen_nn_inputs Ran
ran; our contract draft was wrong, not the code
majingCUHK/Rumor_RvNN/model/BU_RvNN.py
code served (permissive licence) · get_code("e35d6ee7ce9b2f3c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

class TreeNode:
    """Simple tree node class for testing."""
    def __init__(self, word=None, index=None, children=None):
        self.word = word
        self.index = index
        self.children = children if children is not None else []
        self.idx = None

# Build a simple tree structure
# Tree structure:
#       root(w=5, i=5)
#      /            \
#   node1(w=3,i=3)  node2(w=4,i=4)
#   /    \
# leaf1  leaf2
# (w=1,i=1) (w=2,i=2)

leaf1 = TreeNode(word=1, index=1, children=[])
leaf2 = TreeNode(word=2, index=2, children=[])
node1 = TreeNode(word=3, index=3, children=[leaf1, leaf2])
node2 = TreeNode(word=4, index=4, children=[])
root = TreeNode(word=5, index=5, children=[node1, node2])

ARGS = {
    'root_node': root,
    'max_degree': 2,
    'only_leaves_have_vals': True,
    'with_labels': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
gen_nn_inputs Ran
ran; our contract draft was wrong, not the code
majingCUHK/Rumor_RvNN/model/TD_RvNN.py
code served (permissive licence) · get_code("1937b7b7d52a278c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

class TreeNode:
    def __init__(self, idx, word=None, index=None, children=None):
        self.idx = idx
        self.word = word
        self.index = index
        self.children = children if children is not None else []

# Create a simple tree structure for testing
# Root node with two children
leaf1 = TreeNode(idx=0, word=5, index=10, children=[])
leaf2 = TreeNode(idx=1, word=7, index=20, children=[])
root_node = TreeNode(idx=2, word=3, index=15, children=[leaf1, leaf2])

ARGS = {
    "root_node": root_node,
    "ini_word": 42
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
evaluation Not yet run
unverified (harvested, no recorded run)
majingCUHK/Rumor_RvNN/model/evaluate.py
code served (permissive licence) · get_code("a3772b851907a3b6")
How it ran

no invocation recorded.

evaluation_4class Not yet run
unverified (harvested, no recorded run)
majingCUHK/Rumor_RvNN/model/evaluate.py
code served (permissive licence) · get_code("bcd36a3fa1e13855")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 5 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.

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

In recent years, the rapid evolution of large vision-language models (LVLMs) has driven a paradigm shift in multimodal fake news detection (MFND), transforming it from traditional feature-engineering approaches to unified, end-to-end multimodal reasoning frameworks. Early methods primarily relied on shallow fusion techniques to capture correlations between text and images, but they struggled with high-level semantic understanding and complex cross-modal interactions. The emergence of LVLMs has fundamentally changed this landscape by enabling joint modeling of vision and language with powerful representation learning, thereby enhancing the ability to detect misinformation that leverages both textual narratives and visual content. Despite these advances, the field lacks a systematic survey that traces this transition and consolidates recent developments. To address this gap, this paper provides a comprehensive review of MFND through the lens of LVLMs. We first present a historical perspective, mapping the evolution from conventional multimodal detection pipelines to foundation model-driven paradigms. Next, we establish a structured taxonomy covering model architectures, datasets, and performance benchmarks. Furthermore, we analyze the remaining technical challenges, including interpretability, temporal reasoning, and domain generalization. Finally, we outline future research directions to guide the next stage of this paradigm shift. To the best of our knowledge, this is the first comprehensive survey to systematically document and analyze the transformative role of LVLMs in combating multimodal fake news. The summary of existing methods mentioned is in our Github: https://github.com/Tan-YiLong/Overview-of-Fake-News-Detection.

For agents

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

get_harvested_code_for_paper("2601.15316")
get_code_for_paper("2601.15316")
have("2601.15316")

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

curl https://syntology.ai/api/ran/2601.15316.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.15316.svg)](https://syntology.ai/paper/2601.15316)

Connect an agent — have() is free.