Related papers: Ordering stakeholder viewpoint concerns for holist…
Natural language prompts often suffer from intent transmission loss: the gap between what users actually need and what they communicate to AI systems. We evaluate PPS (Prompt Protocol Specification), a 5W3H-based framework for structured…
This paper introduces LalaEval, a holistic framework designed for the human evaluation of domain-specific large language models (LLMs). LalaEval proposes a comprehensive suite of end-to-end protocols that cover five main components…
As product complexity and marketing competition increase, a collaborative product development is necessary for companies which develop high quality products in short lead-times. To support product actors from different fields, disciplines,…
Requirements Engineering (RE) is closely tied to other development activities and is at the heart and foundation of every software development process. This makes RE the most data and communication-intensive activity compared to other…
Context: Recent software engineering (SE) research has highlighted the need for sociotechnical research, implying a demand for customized psychometric scales. Objective: We define the concepts of technical and sociotechnical infrastructure…
Attention regulates information transfer between tokens. For this, query and key vectors are compared, typically in terms of a scalar product, $\mathbf{Q}^T\mathbf{K}$, together with a subsequent softmax normalization. In geometric terms,…
Existing large language models (LLMs) driven search agents typically rely on prompt engineering to decouple the user queries into search plans, limiting their effectiveness in complex scenarios requiring reasoning. Furthermore, they suffer…
Explainable Artificial Intelligence (AI) focuses on helping humans understand the working of AI systems or their decisions and has been a cornerstone of AI for decades. Recent research in explainability has focused on explaining the…
Vision evaluations are typically done through multi-step processes. In most contemporary fields, experts analyze images using structured, evidence-based adaptive questioning. In plant pathology, botanists inspect leaf images, identify…
A dialogue is successful when there is alignment between the speakers at different linguistic levels. In this work, we consider the dialogue occurring between interlocutors engaged in a collaborative learning task, where they are not only…
Enterprise meeting environments require AI assistants that handle diverse operational tasks, from rapid fact checking during live discussions to cross meeting analysis for strategic planning, under strict latency, cost, and privacy…
Finite Element Analysis (FEA) serves as the cornerstone of modern engineering design. However, its workflow is inherently complex and relies heavily on domain expertise. Although recent efforts have integrated Large Language Models (LLMs)…
The ability to build and reason about models of the world is essential for situated language understanding. But evaluating world modeling capabilities in modern AI systems -- especially those based on language models -- has proven…
With the rise of large language models (LLMs), ensuring they embody the principles of being helpful, honest, and harmless (3H), known as Human Alignment, becomes crucial. While existing alignment methods like RLHF, DPO, etc., effectively…
Despite the development of numerous visual analytics tools for event sequence data across various domains, including but not limited to healthcare, digital marketing, and user behavior analysis, comparing these domain-specific…
Large language models excel on objectively verifiable tasks such as math and programming, where evaluation reduces to unit tests or a single correct answer. In contrast, real-world enterprise work is often subjective and context-dependent:…
Document-level Event Argument Extraction (EAE) requires the model to extract arguments of multiple events from a single document. Considering the underlying dependencies between these events, recent efforts leverage the idea of "memory",…
In the international standard for system and software engineering ISO/IEC/IEEE 15288: 2015, the output of the stakeholder needs and the business or mission analysis technical processes are transformed into a technical view of the system by…
Recently, to comprehensively improve Vision Language Models (VLMs) for Visual Question Answering (VQA), several methods have been proposed to further reinforce the inference capabilities of VLMs to independently tackle VQA tasks rather than…
Chain-of-Thought (CoT) prompting has been used to enhance the reasoning capability of LLMs. However, its reliability in security-sensitive analytical tasks remains insufficiently examined, particularly under structured human evaluation.…