相关论文: PRISM: Perspective Reasoning for Integrated Synthe…

Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing to detect complex threats that require deep reasoning. To…

As large language models (LLMs) are increasingly deployed in consequential decision-making contexts, systematically assessing their ethical reasoning capabilities becomes a critical imperative. This paper introduces the Priorities in…

Mutual misunderstanding in contemporary society does not arise merely because people hold different opinions or values. Even under the same observations, different subjects may form different inferential targets, state representations,…

Current approaches to AI safety define red lines at the case level: specific prompts, specific outputs, specific harms. This paper argues that red lines can be set more fundamentally -- at the level of value, evidence, and source…

Traditional agent-based models (ABMs) of opinion dynamics often fail to capture the psychological heterogeneity driving online polarization due to simplistic homogeneity assumptions. This limitation obscures the critical interplay between…

Evaluating vision-language models (VLMs) in scientific domains like mathematics and physics poses unique challenges that go far beyond predicting final answers. These domains demand conceptual understanding, symbolic reasoning, and…

The rapid growth in submissions to machine learning venues has strained the scientific peer-review system and intensified interest in LLM-based automated peer reviewers. However, how good these systems are actually, especially compared to…

Large Language Models are rapidly emerging as web-native interfaces to social platforms. On the social web, users frequently have ambiguous and dynamic goals, making complex intent understanding-rather than single-turn execution-the…

Scaling LLM-based embodied agents from text-only environments to complex multimodal settings remains a major challenge. Recent work identifies a perception-reasoning-decision gap in standalone Vision-Language Models (VLMs), which often…

Explainability remains a critical challenge in artificial intelligence (AI) systems, particularly in high stakes domains such as healthcare, finance, and decision support, where users must understand and trust automated reasoning.…

This paper presents SYMBIOSIS, an AI-powered framework and platform designed to make Systems Thinking accessible for addressing societal challenges and unlock paths for leveraging systems thinking frameworks to improve AI systems. The…

DEEPTHINK methods improve reasoning by generating, refining, and aggregating populations of candidate solutions, which enables strong performance on complex mathematical and scientific tasks. However, existing frameworks often lack reliable…

Human feedback is central to the alignment of Large Language Models (LLMs). However, open questions remain about methods (how), domains (where), people (who) and objectives (to what end) of feedback processes. To navigate these questions,…

Artificial Intelligence (AI) systems are increasingly placed in positions where their decisions have real consequences, e.g., moderating online spaces, conducting research, and advising on policy. Ensuring they operate in a safe and…

Frontier AI systems, including large language models (LLMs), hold increasing influence over the epistemology of human users. Such influence can reinforce prevailing societal values, potentially contributing to the lock-in of misguided moral…

Existing alignment research is dominated by concerns about safety and preventing harm: safeguards, controllability, and compliance. This paradigm of alignment parallels early psychology's focus on mental illness: necessary but incomplete.…

Semantic Text Embedding is a fundamental NLP task that encodes textual content into vector representations, where proximity in the embedding space reflects semantic similarity. While existing embedding models excel at capturing general…

AI systems increasingly shape high-stakes decisions in healthcare, law, defense, and education, yet existing governance paradigms -- AI Ethics, AI Safety, and AI Alignment -- share a common limitation: they evaluate outcomes rather than…

This paper looks at philosophical questions that arise in the context of AI alignment. It defends three propositions. First, normative and technical aspects of the AI alignment problem are interrelated, creating space for productive…

We propose PRISM, a novel framework designed to overcome the limitations of 2D-based Preference-Based Reinforcement Learning (PBRL) by unifying 3D point cloud modeling and future-aware preference refinement. At its core, PRISM adopts a 3D…