Understanding the intricate motivations behind human actions is paramount in developing sophisticated systems capable of nuanced behavior analysis.

Reasoning over TKGs has two challenges: 1.

Fact-checking is considered crucial for limiting the impact of misinformation [Lewandowsky et al.,

Visual question answering ( VQA) is a challenging task that requires an in-depth understanding of vision and language, as well as multi-modal reasoning.

Why was the dataset created? Has the dataset been used already? QA dataset has already been used. QA establishes a framework to benchmark question answering at the present time: answers (e.g., the number of Shohei Ohtani's home runs) change in real time. This could also include the system's interactions with its information retrieval module (for How many instances are there?

We build strong baseline models upon large pretrained language models, including GPT -3 and T5. Our benchmark is an ongoing effort, and this paper presents real-time evaluation results over the past year.

Question answering over visually rich documents (VRDs) requires reasoning not only over isolated content but also over documents' structural organization and cross-page dependencies. However, conventional retrieval-augmented generation (RAG) methods encode content in isolated chunks during ingestion, losing structural and cross-page dependencies, and retrieve a fixed number of pages at inference, regardless of the specific demands of the question or context. This often results in incomplete evidence retrieval and degraded answer quality for multi-page reasoning tasks. To address these limitations, we propose LAD-RAG, a novel Layout-Aware Dynamic RAG framework. During ingestion, LAD-RAG constructs a symbolic document graph that captures layout structure and cross-page dependencies, adding it alongside standard neural embeddings to yield a more holistic representation of the document. During inference, an LLM agent dynamically interacts with the neural and symbolic indices to adaptively retrieve the necessary evidence based on the query. Experiments on MMLongBench-Doc, LongDocURL, DUDE, and MP-DocVQA demonstrate that LAD-RAG improves retrieval, achieving over 90% perfect recall on average without any top-k tuning, and outperforming baseline retrievers by up to 20% in recall at comparable noise levels, yielding higher QA accuracy with minimal latency.

The capacity to reason logically is a hallmark of human cognition.

Textual claims are often accompanied by images to enhance their credibility and spread on social media, but this also raises concerns about the spread of misinformation. Existing datasets for automated verification of image-text claims remain limited, as they often consist of synthetic claims and lack evidence annotations to capture the reasoning behind the verdict. In this work, we introduce AVerImaTeC, a dataset consisting of 1,297 real-world image-text claims. Each claim is annotated with question-answer (QA) pairs containing evidence from the web, reflecting a decomposed reasoning regarding the verdict. We mitigate common challenges in fact-checking datasets such as contextual dependence, temporal leakage, and evidence insufficiency, via claim normalization, temporally constrained evidence annotation, and a two-stage sufficiency check. We assess the consistency of the annotation in AVerImaTeC via inter-annotator studies, achieving a $κ=0.742$ on verdicts and $74.7\%$ consistency on QA pairs. We also propose a novel evaluation method for evidence retrieval and conduct extensive experiments to establish baselines for verifying image-text claims using open-web evidence.