English
Related papers

Related papers: AI Alignment via Incentives and Correction

200 papers

In the future, artificial learning agents are likely to become increasingly widespread in our society. They will interact with both other learning agents and humans in a variety of complex settings including social dilemmas. We argue that…

Artificial Intelligence · Computer Science 2022-02-22 Tobias Baumann

Given that AI systems are set to play a pivotal role in future decision-making processes, their trustworthiness and reliability are of critical concern. Due to their scale and complexity, modern AI systems resist direct interpretation, and…

Artificial Intelligence · Computer Science 2025-01-03 Binxia Xu , Antonis Bikakis , Daniel Onah , Andreas Vlachidis , Luke Dickens

Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool…

As AI adoption expands across human society, the problem of aligning AI models to match human preferences remains a grand challenge. Currently, the AI alignment field is deeply divided between behavioral and representational approaches,…

Computers and Society · Computer Science 2025-08-12 Ben Y. Reis , William La Cava

Artificial intelligence systems, especially those using machine learning, are being deployed in domains from hiring to loan issuance in order to automate these complex decisions. Judging both the effectiveness and fairness of these AI…

Artificial Intelligence · Computer Science 2025-07-04 Disa Sariola , Patrick Button , Aron Culotta , Nicholas Mattei

Reward models (RMs) are crucial for the training and inference-time scaling up of large language models (LLMs). However, existing reward models primarily focus on human preferences, neglecting verifiable correctness signals which have shown…

Computation and Language · Computer Science 2025-02-27 Hao Peng , Yunjia Qi , Xiaozhi Wang , Zijun Yao , Bin Xu , Lei Hou , Juanzi Li

Artificial and biological systems may evolve similar computational solutions despite fundamental differences in architecture and learning mechanisms -- a form of convergent evolution. We demonstrate this phenomenon through large-scale…

Neurons and Cognition · Quantitative Biology 2025-07-04 Guobin Shen , Dongcheng Zhao , Yiting Dong , Qian Zhang , Yi Zeng

LLM agents in markets present algorithmic collusion risks. While prior work shows LLM agents reach supracompetitive prices through tacit coordination, existing research focuses on hand-crafted prompts. The emerging paradigm of prompt…

Artificial Intelligence · Computer Science 2026-04-21 Yingtao Tian

We formalize AI alignment as a multi-objective optimization problem called $\langle M,N,\varepsilon,\delta\rangle$-agreement, in which a set of $N$ agents (including humans) must reach approximate ($\varepsilon$) agreement across $M$…

Artificial Intelligence · Computer Science 2025-11-20 Aran Nayebi

This paper critically evaluates the attempts to align Artificial Intelligence (AI) systems, especially Large Language Models (LLMs), with human values and intentions through Reinforcement Learning from Feedback (RLxF) methods, involving…

Principle-based alignment often lacks context sensitivity and completeness. Grounded in Theory of Mind, we propose role conditioning as a compact alternative: social roles (e.g., mother, judge) implicitly encode both values and the…

Computers and Society · Computer Science 2026-02-03 Zhou Ziheng , Jiakun Ding , Zhaowei Zhang , Ruosen Gao , Yingnian Wu , Demetri Terzopoulos , Yipeng Kang , Fangwei Zhong , Junqi Wang

The burgeoning integration of artificial intelligence (AI) into human society brings forth significant implications for societal governance and safety. While considerable strides have been made in addressing AI alignment challenges,…

Artificial Intelligence · Computer Science 2025-06-17 Zhaowei Zhang , Fengshuo Bai , Mingzhi Wang , Haoyang Ye , Chengdong Ma , Yaodong Yang

AI alignment considers how we can encode AI systems in a way that is compatible with human values. The normative side of this problem asks what moral values or principles, if any, we should encode in AI. To this end, we present a framework…

Computers and Society · Computer Science 2023-01-11 Betty Li Hou , Brian Patrick Green

Current AI alignment paradigms rely on behavioral correction: external supervisors (e.g., RLHF) observe outputs, judge against preferences, and adjust parameters. This paper argues that behavioral correction is structurally analogous to an…

Computers and Society · Computer Science 2026-04-16 Rui Chai

Language model (LM) alignment improves model outputs to reflect human preferences while preserving the capabilities of the base model. The most common alignment approaches are (i) reinforcement learning, which maximizes the expected reward…

Machine Learning · Computer Science 2026-05-11 Lucas Monteiro Paes , Natalie Mackraz , Barry-John Theobald , Federico Danieli

Artificial Intelligence (AI) has been used extensively in automatic decision making in a broad variety of scenarios, ranging from credit ratings for loans to recommendations of movies. Traditional design guidelines for AI models focus…

Artificial Intelligence · Computer Science 2018-09-27 Marisa Vasconcelos , Carlos Cardonha , Bernardo Gonçalves

The evolution of Large Language Model (LLM) reasoning is bottlenecked by the scarcity of high-quality process data. While self-alignment via endogenous rewards offers a solution, mining valid supervision faces three challenges: (1) Label…

Artificial Intelligence · Computer Science 2026-05-26 Yanyu Chen , Jiyue Jiang , Dianzhi Yu , Zheng Wu , Jiahong Liu , Jiaming Han , Xiao Guo , Jinhu Qi , Yu Li , Yifei Zhang , Irwin King

While research on human-AI collaboration exists, it mainly examined language learning and used traditional counting methods with little attention to evolution and dynamics of collaboration on cognitively demanding tasks. This study examines…

Human-Computer Interaction · Computer Science 2025-08-18 Mohammed Saqr , Kamila Misiejuk , Sonsoles López-Pernas

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,…

Computation and Language · Computer Science 2026-03-10 Weixiang Zhao , Haozhen Li , Yanyan Zhao , xuda zhi , Yongbo Huang , Hao He , Bing Qin , Ting Liu

Reward hacking--where agents exploit flaws in imperfect reward functions rather than performing tasks as intended--poses risks for AI alignment. Reward hacking has been observed in real training runs, with coding agents learning to…

Artificial Intelligence · Computer Science 2025-08-26 Mia Taylor , James Chua , Jan Betley , Johannes Treutlein , Owain Evans