Assistants on assembly tasks show great potential to benefit humans ranging from helping with everyday tasks to interacting in industrial settings. However, evaluation resources in assembly activities are underexplored. To foster system development, we propose a new multimodal QA evaluation dataset on assembly activities. Our dataset, ProMQA-Assembly, consists of 646 QA pairs that require multimodal understanding of human activity videos and their instruction manuals in an online-style manner. For cost effectiveness in the data creation, we adopt a semi-automated QA annotation approach, where LLMs generate candidate QA pairs and humans verify them. We further improve QA generation by integrating fine-grained action labels to diversify question types. Additionally, we create 81 instruction task graphs for our target assembly tasks. These newly created task graphs are used in our benchmarking experiment, as well as in facilitating the human verification process. With our dataset, we benchmark models, including competitive proprietary multimodal models. We find that ProMQA-Assembly contains challenging multimodal questions, where reasoning models showcase promising results. We believe our new evaluation dataset contributes to the further development of procedural-activity assistants.

Quantifying uncertainty in large language models (LLMs) is crucial for applications where safety is a concern, as it helps identify factually incorrect LLM answers, commonly referred to as hallucinations. Recently, advancements have been made in quantifying uncertainty, specifically by incorporating the semantics of sampled answers to estimate entropy. These methods typically rely on a normalized probability that is calculated using a limited number of sampled answers. However, we note these estimation methods fail to account for the effects of the semantics that are possible to be obtained as answers, but are not observed in the sample. This is a significant oversight, since a heavier tail of unobserved answer probabilities indicates a higher level of overall uncertainty. To alleviate this issue, we propose Evidential Semantic Entropy (EVSE), which leverages evidence theory to represent both total ignorance arising from unobserved answers and partial ignorance stemming from the semantic relationships among the observed answers. Experiments show that EVSE significantly improves uncertainty quantification performance. Our code is available at: https://github.com/lucieK-J/EvidentialSemanticEntropy.git.

Large Language Models (LLMs) provide flexible natural language processing capabilities, while knowledge graphs (KGs) offer explicit and structured knowledge. Integrating these two in a complementary manner enables the development of reliable and verifiable AI systems. In particular, knowledge graph question answering (KGQA) has attracted attention as a means to reduce LLM hallucinations and to leverage knowledge beyond the training data. However, existing KGQA benchmark datasets are biased toward encyclopedic knowledge, limited to a single modality, and lack fine-grained spatiotemporal data, which limits their applicability to real-world scenarios targeted by Embodied AI. We introduce HOME-KGQA, a novel KGQA benchmark dataset built on a multimodal KG of daily household activities. HOME-KGQA consists of complex, multi-hop natural language questions paired with graph database query languages. Compared to existing benchmarks, it includes more challenging questions that involve multi-level spatiotemporal reasoning, multimodal grounding, and aggregate functions. Experimental results show that the LLM-based KGQA methods fail to achieve performance comparable to that on existing datasets when evaluated on HOME-KGQA. This highlights significant challenges that should be addressed for the real-world deployment of KGQA systems. Our dataset is available at https://github.com/aistairc/home-kgqa.

We present VDAct 2.0, an enhanced benchmark for video-grounded dialogue that builds upon the original VDAct by expanding dialogue coverage and introducing a scalable LLM-assisted filtering pipeline to ensure high-quality, grounded QA pairs. VDAct 2.0 comprises 6,356 human-annotated dialogues with a total of 63,958 turns, grounded in 2,975 household activity videos, with undesirable dialogue turns systematically identified and removed. To achieve this, we design a trigger-based quality framework and calibrate a panel of high-agreement LLMs through human-in-the-loop calibration, allowing scalable QA-turn-level filtering. We benchmark a wide range of pretrained and fine-tuned models, both open-source and proprietary, across standard text generation metrics and LLM-based evaluations. The results highlight both recent advances and remaining challenges in video-grounded dialogue modeling, positioning VDAct 2.0 as a high-fidelity testbed for evaluating and advancing multimodal reasoning in interactive settings.

Quantifying uncertainty in large language models (LLMs) is important for safety-critical applications because it helps spot incorrect answers, known as hallucinations. One major trend of uncertainty quantification methods is based on estimating the entropy of the distribution of the LLM’s potential output sequences. This estimation is based on a set of output sequences and associated probabilities obtained by querying the LLM several times. In this paper, we advocate and experimentally and show that the probability of unobserved sequences plays a crucial role, and we recommend future research to integrate it to enhance such LLM uncertainty quantification methods.

Multimodal systems have great potential to assist humans in procedural activities, where people follow instructions to achieve their goals. Despite diverse application scenarios, systems are typically evaluated on traditional classification tasks, e.g., action recognition or temporal action localization. In this paper, we present a novel evaluation dataset, ProMQA, to measure the advancement of systems in application-oriented scenarios. ProMQA consists of 401 multimodal procedural QA pairs on user recording of procedural activities, i.e., cooking, coupled with their corresponding instruction. For QA annotation, we take a cost-effective human-LLM collaborative approach, where the existing annotation is augmented with LLM-generated QA pairs that are later verified by humans. We then provide the benchmark results to set the baseline performance on ProMQA. Our experiment reveals a significant gap between human performance and that of current systems, including competitive proprietary multimodal models. We hope our dataset sheds light on new aspects of models’ multimodal understanding capabilities.

This paper presents a schema-aware end-to-end neural network model for handling task-oriented dialogues based on a dynamic set of slots within a schema. Contrary to existing studies that proposed end-to-end approaches for task-oriented dialogue systems by relying on a unified schema across domains, we design our approach to support a domain covering multiple services where diverse schemas are available. To enable better generalizability among services and domains with different schemas, we supply the schema’s context information including slot descriptions and value constraints to the model. The experimental results on a well-known Schema-Guided Dialogue (SGD) dataset demonstrated the performance improvement by the proposed model compared to state-of-the-art baselines in terms of end-to-end modeling, dialogue state tracking task, and generalization on new services and domains using a limited number of dialogues.