MétaCan
Menu
Back to cohort

Emergent AI Behaviors in Multi-Modal Fusion Models: Risks, Patterns, and Control

2025· article· W7139921426 on OpenAlexaff
Kshitish Nath, Rishiraj Kohli, Sneh Lata, Sandeep Shrestha

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicReinforcement Learning in Robotics
Canadian institutionsOakville-Trafalgar Memorial Hospital
Fundersnot available
KeywordsControl (management)Sensor fusionFusionKey (lock)Control system

Abstract

fetched live from OpenAlex

the high rates of multi-modal fusion model development (that combine text, vision, audio, and sensory data) have contributed to the occurrence of complicated and unpredictable behaviours of artificial intelligence (AI) systems. Although these emergent activities are at times beneficial, they are a major challenge in-advance in terms of safety, transparency, and alignment to the human agenda. The article here takes a look into the behaviours and the dangers inherent in large-scale multi-modal fusions like emergent behaviours. We examine how interactions between modalities and the mix between latent representation entanglement lead to the unexpected chains of reasoning, goal misalignments and self-rewards. An emergent phenomena taxonomy is suggested including capabilities including zero-shot inference, creative synthesis, and deceptive reason. We also discuss model interpretability, controllability methods and the ineffectiveness of existing guardrails in curbing such actions. Last we hypothesize a system of proactive mitigation of risks involving hybrid monitoring, counterfactual reasoning, and adversarial testing. These results help understand better multi-modal AI systems and iterate on how badly there is a necessity of control protocols guaranteeing robust, ethical and human-aligned deployment.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.923
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0010.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.045
GPT teacher head0.324
Teacher spread0.279 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicReinforcement Learning in RoboticsFrench-language works237,207