This paper introduces the Cross-Modal Conflict Benchmark (CMC-Bench) to evaluate how multimodal retrieval-augmented generation (RAG) systems handle contradicting evidence between retrieved text and images. Using 3,768 instances from ChartQA and MMMU evaluation splits, the study benchmarks four open vision-language models (VLMs) across four conflict types (factual, temporal, entity, and granularity) and four evidence conditions: aligned (both modalities support the gold answer), image-correct (image supports the gold and text contradicts it), text-correct (text supports the gold and the image is wrong or swapped), and both-wrong(neither modality supports the gold). Key findings reveal that cross-modal disagreement severely degrades performance, with change in accuracy between 0.17 and 0.46 relative to aligned evidence. Results show models often exhibit a modality lean rather than reliable arbitration, with text-leaning systems particularly vulnerable when only the image is correct. Furthermore, merging abstention and fabrication into a single hallucination score obscures critical behavioral differences; for instance, Qwen3-VL-4B abstains on 31.7% of conflicts, while Gemma-3n-E2B fabricates unsupported answers in 51.9% of conflicts. Multimodal RAG evaluation should explicitly distinguish abstention from fabrication to assess reliability accurately.

The critique of scalar benchmark rankings as proxies for model quality is now well-established (Raji et al., 2021; Wallach et al.,2025; Bean et al., 2025; Gehrmann et al., 2021). What the field still lacks is a shared structural vocabulary for comparing, combining, and contextualizing metric design choices. This paper provides that vocabulary: a four-primitive typology—representation (𝜙), comparison (D), aggregation (A), and context (C)—under which existing metrics (BLEU, BERTScore, nDCG, LLM-as-judge, calibration scores, agentic outcome measures) are explicit parameterizations of a common form. This typology is paired with a measurement–decision split: metrics are noisy estimators of latent constructs, and model selection is context-dependent Pareto optimization over construct estimates, not over raw scores. The typology makes implicit metric assumptions comparable and debatable rather than hidden inside a single number.

Current automated content moderation systems fail to protect children from harmful YouTube content, particularly in under-resourced, code-switched settings. These systems are often text-only, English-centric, and operate as ’black boxes,’ lacking the multimodal understanding and transparency needed for effective moderation. This thesis proposes a novel hybrid framework for the explainable multimodal detection of harmful content in videos with code-switching. The proposed framework integrates a fine-tuned classifier for accurate, scalable detection with an LLM-powered module that synthesizes the classifier’s internal evidential signals (e.g., text attention and visual heat maps) to generate faithful, human-readable rationales for each decision. As a primary case study, the framework will be developed and validated on an English–Filipino code-switched dataset. Expected contributions include a new dataset publicly available under controlled access (de-identified transcripts, blacked-out frames, extracted feature representations, and metadata via data-sharing agreement) and a blueprint for building more equitable, transparent, and trustworthy AI safety systems.

Grasping morality is vital in AI systems, particularly as they become more prevalent in human-focused applications. Yet, research is scarce on this topic. This study presents the Emotion-based Morality in Tagalog and English Scenarios (EMoTES-3K), a collection that shows commonsense morality in both Filipino and English. This dataset is instrumental for analyzing moral decisions in various situations and their justifications. Our tests show that EMoTES-3K is effective for moral text categorization, with the fine-tuned RoBERTa model scoring 94.95% accuracy in English and 88.53% in Filipino. The dataset also excels in text generation tasks, as shown by fine-tuning the FLAN-T5 model to produce clear moral explanations. However, the model faces challenges when dealing with actions that have mixed moral implications. This work not only bridges the gap in moral reasoning datasets for languages like Filipino but also sets the stage for future research in commonsense moral reasoning in artificial intelligence.