arXiv:2608. 12372v1 Announce Type: new Abstract: AI systems are increasingly employed as decision aids, decision delegates, or autonomous decision-makers.
arXiv:2607. 14240v1 Announce Type: new Abstract: Current alignment approaches typically focus on emulating human behavior using static representations of human preferences, failing to capture the dynamic, context-dependent nature of real-world human-AI interactions.
arXiv:2608.30842v1 Announce Type: new Abstract: Humans play a vital role at every stage of AI development, from data collection and curation to model development and evaluation. However, humans often...
arXiv:2604. 21827v2 Announce Type: replace Abstract: In accomplishing complex tasks, human cognition typically progresses from abstract to concrete (e.
arXiv:2606. 12754v1 Announce Type: cross Abstract: Are large language models (LLMs) bad at capturing human judgment?
arXiv:2608. 10327v1 Announce Type: new Abstract: Can AI systems be aligned to human values?
The article surveys AI alignment from a game-theoretic perspective, focusing on how large language models and AI agents can be aligned with complex human values in high-risk settings. It categorizes recent progress around key game-theoretic elements and addresses three main challenges: preference diversity, alignment priority, and temporal dynamics. The survey clarifies where game theory benefits current alignment methods, where its application is looser, and what remains to be tackled for robust, adaptive, and verifiable AI systems.
The paper investigates whether reasoning representations—explanations for large language model outputs—aid humans in evaluating those outputs. A controlled human study tested six reasoning formats across tasks of varying complexity, measuring structural understanding, error detection, and trust calibration. Results revealed a mismatch: participants favored planning- and decomposition-based representations, yet simpler chain-of-thought traces better supported verification, trust, and interpretability, while preferred formats increased calibration risks.
We are improving our AI systems’ ability to learn from human feedback and to assist humans at evaluating AI. Our goal is to build a sufficiently aligned AI system that can help us solve all other alignment problems.
arXiv:2608. 12325v1 Announce Type: new Abstract: Autonomous reasoning is among the most scientifically and economically motivating topics in AI today.
arXiv:2606. 06081v1 Announce Type: new Abstract: Appropriate reliance on AI advice has become a central research theme in human-AI collaboration.
The study investigates how different AI support formats influence human decision-making across two tasks: abstract visual reasoning with RAVEN matrices and deductive logical reasoning with LSAT problems. Findings reveal that in visual reasoning, predictions alone and predicted probabilities best support accuracy and error recovery, while in logical reasoning, LLM explanations outperform other supports. The results suggest that effective human–AI collaboration requires task‑specific support strategies rather than a one‑size‑fits‑all approach.
The study examines how the effort expended by large reasoning models (LRMs) compares to that of humans during abductive reasoning tasks. By analyzing reaction times and reasoning traces, the authors find that LRMs and humans exhibit similar patterns of effort and error types. They also demonstrate that decoding strategies allowing models to explore multiple reasoning paths further align the models’ reasoning costs with human effort.