Related papers: PRISM: Perspective Reasoning for Integrated Synthe…
As large language models (LLMs) evolve into autonomous agents capable of acting in open-ended environments, ensuring behavioral alignment with human values becomes a critical safety concern. Existing benchmarks, focused on static,…
Large language models (LLMs) are increasingly used in human-AI interaction research and practice, yet existing capability and safety benchmarks reveal little about the value priorities these systems express or how those priorities…
Evaluating moral alignment in agents navigating conflicting, hierarchically structured human norms is a critical challenge at the intersection of AI safety, moral philosophy, and cognitive science. We introduce Morality Chains, a novel…
The rapid proliferation of multimodal social media content has driven research in Multimodal Conversational Stance Detection (MCSD), which aims to interpret users' attitudes toward specific targets within complex discussions. However,…
Pluralistic alignment is typically operationalised as preference aggregation: producing responses that span (Overton), steer toward (Steerable), or proportionally represent (Distributional) diverse human values. We argue that aggregation…
The increasing use of Artificial Intelligence (AI) in critical societal domains has amplified concerns about fairness, particularly regarding unequal treatment across sensitive attributes such as race, gender, and socioeconomic status.…
Artificial intelligence (AI) is advancing at a pace that raises urgent questions about how to align machine decision-making with human moral values. This working paper investigates how leading AI systems prioritize moral outcomes and what…
We introduce \prism{} (\textbf{P}robabilistic \textbf{R}etrieval with \textbf{I}nformation-\textbf{S}tratified \textbf{M}emory), an evolutionary memory substrate for multi-agent AI systems engaged in open-ended discovery. \prism{} unifies…
Benchmarks for competition-style reasoning have advanced evaluation in mathematics and programming, yet physics remains comparatively explored. Most existing physics benchmarks evaluate only final answers, which fail to capture reasoning…
Process Reward Models (PRMs) are crucial in complex reasoning and problem-solving tasks (e.g., LLM agents with long-horizon decision-making) by verifying the correctness of each intermediate reasoning step. In real-world scenarios, LLMs may…
The question of whether artificial entities deserve moral consideration has become one of the defining ethical challenges of AI research. Existing frameworks for moral patiency rely on verified ontological properties, such as sentience,…
Contemporary artificial intelligence research has been organized around two dominant ambitions: productivity, which treats AI systems as tools for accelerating work and economic output, and alignment, which focuses on ensuring that…
Although LLMs have made substantial progress in reasoning, systematically producing frontier-level reasoning data remains difficult. Existing synthesis methods often have limited visibility into the structural factors that govern problem…
As AI agents become increasingly autonomous, widely deployed in consequential contexts, and efficacious in bringing about real-world impacts, ensuring that their decisions are not only instrumentally effective but also normatively aligned…
As AI systems become increasingly sophisticated, questions about machine consciousness and its ethical implications have moved from fringe speculation to mainstream academic debate. Current ethical frameworks in this domain often implicitly…
What values, evidence preferences, and source trust hierarchies do AI systems actually exhibit when facing structured dilemmas? We present the first large-scale empirical mapping of AI decision-making across all three layers of the…
Multimodal large language models (MLLMs) have achieved remarkable progress on vision-language tasks, yet their reasoning processes remain sometimes unreliable. We introduce PRISM-Bench, a benchmark of puzzle-based visual challenges designed…
Video dataset condensation aims to reduce the immense computational cost of video processing. However, it faces a fundamental challenge regarding the inseparable interdependence between spatial appearance and temporal dynamics. Prior work…
The critical inquiry pervading the realm of Philosophy, and perhaps extending its influence across all Humanities disciplines, revolves around the intricacies of morality and normativity. Surprisingly, in recent years, this thematic thread…
Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit preferences (including…