Related papers: PRISM: Perspective Reasoning for Integrated Synthe…
Automated interpretability research aims to identify concepts encoded in neural network features to enhance human understanding of model behavior. Within the context of large language models (LLMs) for natural language processing (NLP),…
Case studies commonly form the pedagogical backbone in law, ethics, and many other domains that face complex and ambiguous societal questions informed by human values. Similar complexities and ambiguities arise when we consider how AI…
Instruction-tuned Large Language Models (LLMs) are increasingly deployed as AI Assistants in firms for support in cognitive tasks. These AI assistants carry embedded perspectives which influence factors across the firm including…
Current AI safety frameworks, which often treat harmfulness as binary, lack the flexibility to handle borderline cases where humans meaningfully disagree. To build more pluralistic systems, it is essential to move beyond consensus and…
Artificial intelligence (AI) technologies should adhere to human norms to better serve our society and avoid disseminating harmful or misleading information, particularly in Conversational Information Retrieval (CIR). Previous work,…
E-commerce search systems rely on modeling user behavior to estimate item relevance and user preference, which are typically assumed to be stable and independently learnable signals. However, in practice, user interactions are jointly…
Self-evolving reasoning frameworks let LLMs improve their reasoning capabilities by iteratively generating and solving problems without external supervision, using verifiable rewards. Ideally, such systems are expected to explore a diverse…
A core component of human intelligence is the ability to identify abstract patterns inherent in complex, high-dimensional perceptual data, as exemplified by visual reasoning tasks such as Raven's Progressive Matrices (RPM). Motivated by the…
Solving the AI alignment problem requires having clear, defensible values towards which AI systems can align. Currently, targets for alignment remain underspecified and do not seem to be built from a philosophically robust structure. We…
Background: Increasingly, decision-making in healthcare relies on computer models, be it clinical prediction models at point of care or decision-analytic models at the policymaking level. Given the important role models play in both…
Generative Sequential Recommendation (GSR) has emerged as a promising paradigm, reframing recommendation as an autoregressive sequence generation task over discrete Semantic IDs (SIDs), typically derived via codebook-based quantization.…
Spatial reasoning is a core aspect of human intelligence that allows perception, inference and planning in 3D environments. However, current vision-language models (VLMs) struggle to maintain geometric coherence and cross-view consistency…
As artificial intelligence (AI) improves, traditional alignment strategies may falter in the face of unpredictable self-improvement, hidden subgoals, and the sheer complexity of intelligent systems. Inspired by contemplative wisdom…
Auditing Large Language Models (LLMs) to discover their biases and preferences is an emerging challenge in creating Responsible Artificial Intelligence (AI). While various methods have been proposed to elicit the preferences of such models,…
Humans rapidly learn abstract knowledge when encountering novel environments and flexibly deploy this knowledge to guide efficient and intelligent action. Can modern AI systems learn and plan in a similar way? We study this question using a…
Analogical reasoning is a fundamental capacity of human cognition that allows us to reason abstractly about novel situations by relating them to past experiences. While it is thought to be essential for robust reasoning in AI systems,…
Human values are crucial to human decision-making. Value pluralism is the view that multiple correct values may be held in tension with one another (e.g., when considering lying to a friend to protect their feelings, how does one balance…
Long-horizon language agents accumulate conversation history far faster than any fixed context window can hold, making memory management critical to both answer accuracy and serving cost. Existing approaches either expand the context window…
The deployment of large language models (LLMs) in mental health and other sensitive domains raises urgent questions about ethical reasoning, fairness, and responsible alignment. Yet, existing benchmarks for moral and clinical…
Recent reinforcement-learning frameworks for visual perception policy usually incorporate intermediate reasoning chains expressed in natural language. Empirical observations indicate that such purely linguistic intermediate reasoning often…