GCC AI Research

Search

Results for "Credo AI"

FAID: Fine-Grained AI-Generated Text Detection Using Multi-Task Auxiliary and Multi-Level Contrastive Learning

arXiv ·

MBZUAI researchers introduce FAID, a fine-grained AI-generated text detection framework capable of classifying text as human-written, LLM-generated, or collaboratively written. FAID utilizes multi-level contrastive learning and multi-task auxiliary classification to capture authorship and model-specific characteristics, and can identify the underlying LLM family. The framework outperforms existing baselines, especially in generalizing to unseen domains and new LLMs, and includes a multilingual, multi-domain dataset called FAIDSet.

The AI Pentad, the CHARME$^{2}$D Model, and an Assessment of Current-State AI Regulation

arXiv ·

This paper introduces the AI Pentad model, comprising humans/organizations, algorithms, data, computing, and energy, as a framework for AI regulation. It also presents the CHARME²D Model to link the AI Pentad with regulatory enablers like registration, monitoring, and enforcement. The paper assesses AI regulatory efforts in the EU, China, UAE, UK, and US using the CHARME²D model, highlighting strengths and weaknesses.

The search for an antidote to Byzantine attacks

MBZUAI ·

MBZUAI researchers have developed 'Byzantine antidote' (Bant), a novel defense mechanism against Byzantine attacks in federated learning. Bant uses trust scores and a trial function to dynamically filter and neutralize corrupted updates, even when a majority of nodes are compromised. The research was presented at the 40th Annual AAAI Conference on Artificial Intelligence.

Profiling News Media for Factuality and Bias Using LLMs and the Fact-Checking Methodology of Human Experts

arXiv ·

A new methodology emulating fact-checker criteria assesses news outlet factuality and bias using LLMs. The approach uses prompts based on fact-checking criteria to elicit and aggregate LLM responses for predictions. Experiments demonstrate improvements over baselines, with error analysis on media popularity and region, and a released dataset/code at https://github.com/mbzuai-nlp/llm-media-profiling.

ILION: Deterministic Pre-Execution Safety Gates for Agentic AI Systems

arXiv ·

The paper introduces ILION, a deterministic execution gate designed to ensure the safety of autonomous AI agents by classifying proposed actions as either BLOCK or ALLOW. ILION uses a five-component cascade architecture that operates without statistical training, API dependencies, or labeled data. Evaluation against existing text-safety infrastructures demonstrates ILION's superior performance in preventing unauthorized actions, achieving an F1 score of 0.8515 with sub-millisecond latency.

Beyond the Resumé: A Rubric-Aware Automatic Interview System for Information Elicitation

arXiv ·

MBZUAI researchers have developed an automatic interview system that uses LLMs to elicit nuanced, role-specific information from job candidates, improving early-stage hiring decisions. The system updates its belief about an applicant's rubric-oriented latent traits in a calibrated way based on their interview performance. Evaluation on simulated interviews showed the system's belief converges towards the simulated applicants' constructed ability levels.

Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models

arXiv ·

Researchers at MBZUAI have introduced Video-R2, a reinforcement learning approach to improve the consistency and visual grounding of reasoning in multimodal language models. Video-R2 combines timestamp-aware supervised fine-tuning with Group Relative Policy Optimization (GRPO) guided by a Temporal Alignment Reward (TAR). The model demonstrates higher Think Answer Consistency (TAC), Video Attention Score (VAS), and accuracy across multiple benchmarks, showing improved temporal alignment and reasoning coherence for video understanding.