Related papers: HM-Req: A Framework for Embedding Values within CP…
Large language models (LLMs) are increasingly being used for tasks where outputs shape human decisions, so it is critical to verify that their responses consistently reflect desired human values. Humans, as individuals or groups, don't…
Recent advances in large language models (LLMs) have sparked growing interest in building fully autonomous agents. However, fully autonomous LLM-based agents still face significant challenges, including limited reliability due to…
While procedures prevail on the European market for the greater good of its citizens, it might be daunting when trying to introduce a product, whether innovative or not. In the current world, Cyber-Physical Systems (CPSs) are ubiquitous in…
Ensuring large language models' (LLMs) responses align with prompt instructions is crucial for application development. Based on our formative study with industry professionals, the alignment requires heavy human involvement and tedious…
Human factors/ergonomics (HFE) standards are not only a useful reference for experienced HFE practitioners but can also provide guidance for organizations that are inexperienced in HFE design practice. HFE standards can give credibility to…
The presence of decision-making algorithms in society is rapidly increasing nowadays, while concerns about their transparency and the possibility of these algorithms becoming new sources of discrimination are arising. There is a certain…
Motivated by scaling laws in language modeling that demonstrate how test loss scales as a power law with model and dataset sizes, we find that similar laws exist in preference modeling. We propose World Preference Modeling$ (WorldPM) to…
The explosion of high-performing conversational language models (LMs) has spurred a shift from classic natural language processing (NLP) benchmarks to expensive, time-consuming and noisy human evaluations - yet the relationship between…
Currently, CyberPhysical Systems (CPS) represents a great challenge for automatic control and smart systems engineering on both theoretical and practical levels. Designing CPS requires approaches involving multidisciplinary competences.…
Robots, as AI with physical instantiation, inhabit our social and physical world, where their actions have both social and physical consequences, posing challenges for researchers when designing social robots. This study starts with a…
As audio-first agents become increasingly common in physical AI, conversational robots, and screenless wearables, audio large language models (audio-LLMs) must integrate speaker-specific understanding to support user authorization,…
Value alignment is central to the development of safe and socially compatible artificial intelligence. However, how Large Language Models (LLMs) represent and enact human values in real-world decision contexts remains under-explored. We…
Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared values - a process coined alignment. However, aligning LLMs remains challenging due to the inherent…
Evaluating concept customization is challenging, as it requires a comprehensive assessment of fidelity to generative prompts and concept images. Moreover, evaluating multiple concepts is considerably more difficult than evaluating a single…
Natural-language-facilitated human-robot cooperation (NLC) refers to using natural language (NL) to facilitate interactive information sharing and task executions with a common goal constraint between robots and humans. Recently, NLC…
The increasing complexity of computer science research projects demands more effective tools for deploying code repositories. Large Language Models (LLMs), such as Anthropic Claude and Meta Llama, have demonstrated significant advancements…
Large language models (LLMs) are transforming global decision-making and societal systems by processing diverse data at unprecedented scales. However, their potential to homogenize human values poses critical risks, similar to biodiversity…
Human computer interaction is shifting from screen-based systems to multimodal interfaces where artificial intelligence powered systems increasingly interpret user intent through speech, gesture, and gaze. Yet users rarely understand how…
The overarching, broad topic of my research are advancements in the area of safety-critical, cyber-physical systems (CPS) development with emphasis on validation and verification. The particular focus of my research is the early validation…
Alignment with human preferences is an important evaluation aspect of LLMs, requiring them to be helpful, honest, safe, and to precisely follow human instructions. Evaluating large language models' (LLMs) alignment typically involves…