AIDec 22, 2024

ViLBias: Detecting and Reasoning about Bias in Multimodal Content

arXiv:2412.17052v51 citationsh-index: 8
Originality Incremental advance
AI Analysis

This work addresses bias detection in multimodal content for news analysis, offering a scalable benchmark and baselines, but it is incremental as it builds on existing VQA-style methods and tuning strategies.

The authors tackled the problem of detecting bias in multimodal news by introducing ViLBias, a benchmark and framework for reasoning over text-image pairs, which improved detection accuracy by 3-5% and showed that parameter-efficient tuning methods recover 97-99% of full fine-tuning performance with less than 5% trainable parameters.

Detecting bias in multimodal news requires models that reason over text--image pairs, not just classify text. In response, we present ViLBias, a VQA-style benchmark and framework for detecting and reasoning about bias in multimodal news. The dataset comprises 40,945 text--image pairs from diverse outlets, each annotated with a bias label and concise rationale using a two-stage LLM-as-annotator pipeline with hierarchical majority voting and human-in-the-loop validation. We evaluate Small Language Models (SLMs), Large Language Models (LLMs), and Vision--Language Models (VLMs) across closed-ended classification and open-ended reasoning (oVQA), and compare parameter-efficient tuning strategies. Results show that incorporating images alongside text improves detection accuracy by 3--5\%, and that LLMs/VLMs better capture subtle framing and text--image inconsistencies than SLMs. Parameter-efficient methods (LoRA/QLoRA/Adapters) recover 97--99\% of full fine-tuning performance with $<5\%$ trainable parameters. For oVQA, reasoning accuracy spans 52--79\% and faithfulness 68--89\%, both improved by instruction tuning; closed accuracy correlates strongly with reasoning ($r = 0.91$). ViLBias offers a scalable benchmark and strong baselines for multimodal bias detection and rationale quality.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes