High-quality, multi-modal benchmarks are crucial for advancing scientific reasoning in large models yet their manual creation is costly and unscalable. To address this bottleneck, we explore the potential for transforming Text-Only QA Pairs (TQAs) into high-quality Multi-Modal QA Pairs (MMQAs), which include three parts: 1) Task Definition \& Evaluation Rubric: We develop a TQA-to-MMQA framework and establish a comprehensive, multi-dimensional MMQA quality rubric that provides principles for the transformation. 2) Benchmark Construction: Then we construct two extensive benchmarks to rigorously evaluate state-of-the-art generation \& understanding models on the distinct tasks of MMQA generation \& MMQA quality evaluation. 3) Preliminary Solution: We develop an agentic system (Q-Mirror), which operationalizes our framework by integrating MMQA generation and evaluation into a closed loop for iterative refinement. Our experiments show that while state-of-the-art models can generate MMQAs, their outputs still leave substantial gaps, underscoring the need for reliable evaluation. We further demonstrate that top-tier understanding models align closely with human judgment in MMQA quality assessment. Leveraging both insights, the Q-Mirror agent raises average scores from 78.90 to 85.22 and pass rates from 72\% to 95\%, offering a practical path to large-scale scientific benchmarks.

A canonical example in healthcare is predicting patient outcomes using physiological time-series data, where a population of patients composes a cross-section.

Understanding the mechanisms behind Large Language Models (LLMs) is crucial for designing improved models and strategies. While recent studies have yielded valuable insights into the mechanisms of textual LLMs, the mechanisms of Multimodal Large Language Models (MLLMs) remain underexplored. In this paper, we apply mechanistic interpretability methods to analyze the visual question answering (VQA) mechanisms in Llava. We compare the mechanisms between VQA and textual QA (TQA) in color answering tasks and find that: a) VQA exhibits a mechanism similar to the in-context learning mechanism observed in TQA; b) the visual features exhibit significant interpretability when projecting the visual embeddings into the embedding space; and c) Llava enhances the existing capabilities of the corresponding textual LLM Vicuna during visual instruction tuning. Based on these findings, we develop an interpretability tool to help users and researchers identify important visual locations for final predictions, aiding in the understanding of visual hallucination. Our method demonstrates faster and more effective results compared to existing interpretability approaches. Large Language Models (LLMs) (Brown, 2020; Ouyang et al., 2022; Touvron et al., 2023) have achieved remarkable results in numerous downstream tasks (Xiao et al., 2023; Tan et al., 2023; Deng et al., 2023). However, the underlying mechanisms are not yet well understood. This lack of clarity poses a significant challenge for researchers attempting to address issues such as hallucination (Yao et al., 2023), toxicity (Gehman et al., 2020), and bias (Kotek et al., 2023) in LLMs. Therefore, understanding the mechanisms of LLMs has become an increasingly important area of research.

Text-to-SQL parsing and end-to-end question answering (E2E TQA) are two main approaches for Table-based Question Answering task. Despite success on multiple benchmarks, they have yet to be compared and their synergy remains unexplored. In this paper, we identify different strengths and weaknesses through evaluating state-of-the-art models on benchmark datasets: Text-to-SQL demonstrates superiority in handling questions involving arithmetic operations and long tables; E2E TQA excels in addressing ambiguous questions, non-standard table schema, and complex table contents. To combine both strengths, we propose a Synergistic Table-based Question Answering approach that integrate different models via answer selection, which is agnostic to any model types. Further experiments validate that ensembling models by either feature-based or LLM-based answer selector significantly improves the performance over individual models.

With advancements in Large Language Models (LLMs), a major use case that has emerged is querying databases in plain English, translating user questions into executable database queries, which has improved significantly. However, real-world datasets often feature a vast array of attributes and complex values, complicating the LLMs task of accurately identifying relevant columns or values from natural language queries. Traditional methods cannot fully relay the datasets size and complexity to the LLM. To address these challenges, we propose a novel framework that leverages Full-Text Search (FTS) on the input table. This approach not only enables precise detection of specific values and columns but also narrows the search space for language models, thereby enhancing query accuracy. Additionally, it supports a custom auto-complete feature that suggests queries based on the data in the table. This integration significantly refines the interaction between the user and complex datasets, offering a sophisticated solution to the limitations faced by current table querying capabilities. This work is accompanied by an application for both Mac and Windows platforms, which readers can try out themselves on their own data.

Large Language Models (LLMs), originally shown to ace various text comprehension tasks have also remarkably been shown to tackle table comprehension tasks without specific training. While previous research has explored LLM capabilities with tabular dataset tasks, our study assesses the influence of $\textit{in-context learning}$,$ \textit{model scale}$, $\textit{instruction tuning}$, and $\textit{domain biases}$ on Tabular Question Answering (TQA). We evaluate the robustness of LLMs on Wikipedia-based $\textbf{WTQ}$ and financial report-based $\textbf{TAT-QA}$ TQA datasets, focusing on their ability to robustly interpret tabular data under various augmentations and perturbations. Our findings indicate that instructions significantly enhance performance, with recent models like Llama3 exhibiting greater robustness over earlier versions. However, data contamination and practical reliability issues persist, especially with WTQ. We highlight the need for improved methodologies, including structure-aware self-attention mechanisms and better handling of domain-specific tabular data, to develop more reliable LLMs for table comprehension.

Many automated planning methods and formulations rely on suitably designed abstractions or simplifications of the constrained dynamics associated with agents to attain computational scalability. We consider formulations of temporal planning where intervals are associated with both action and fluent atoms, and relations between these are given as sentences in Allen's Interval Logic. We propose a notion of planning graphs that can account for complex concurrency relations between actions and fluents as a Constraint Programming (CP) model. We test an implementation of our algorithm on a state-of-the-art framework for CP and compare it with PDDL 2.1 planners that capture plans requiring complex concurrent interactions between agents. We demonstrate our algorithm outperforms existing PDDL 2.1 planners in the case studies. Still, scalability remains challenging when plans must comply with intricate concurrent interactions and the sequencing of actions.

Textbook Question Answering (TQA) is a complex multimodal task to infer answers given large context descriptions and abundant diagrams. Compared with Visual Question Answering (VQA), TQA contains a large number of uncommon terminologies and various diagram inputs. It brings new challenges to the representation capability of language model for domain-specific spans. And it also pushes the multimodal fusion to a more complex level. To tackle the above issues, we propose a novel model named MoCA, which incorporates multi-stage domain pretraining and multimodal cross attention for the TQA task. Firstly, we introduce a multi-stage domain pretraining module to conduct unsupervised post-pretraining with the span mask strategy and supervised pre-finetune. Especially for domain post-pretraining, we propose a heuristic generation algorithm to employ the terminology corpus. Secondly, to fully consider the rich inputs of context and diagrams, we propose cross-guided multimodal attention to update the features of text, question diagram and instructional diagram based on a progressive strategy. Further, a dual gating mechanism is adopted to improve the model ensemble. The experimental results show the superiority of our model, which outperforms the state-of-the-art methods by 2.21% and 2.43% for validation and test split respectively.