Your personalresearch library

Discover papers, track what you're reading, rate and review.Build a library that grows with your curiosity.

Get Started Explore Papers

Currently Reading

Want to Read

All Papers

Publication Date

Newest Oldest

Average Rating

Highest Lowest

Value Alignment of Social Media Ranking Algorithms

Farnaz Jahanbakhsh, Dora Zhao, Tiziano Piccardi, Zachary Robertson, Ziv Epstein, Sanmi Koyejo, Michael S. Bernstein

arXiv·2025

While social media feed rankings are primarily driven by engagement signals rather than any explicit value system, the resulting algorithmic feeds are not value-neutral: engagement may prioritize specific individualistic values. This paper presents an approach for social media feed value alignment. We adopt Schwartz's theory of Basic Human Values -- a broad set of human values that articulates complementary and opposing values forming the building blocks of many cultures -- and we implement an algorithmic approach that models and then ranks feeds by expressions of Schwartz's values in social media posts. Our approach enables controls where users can express weights on their desired values, combining these weights and post value expressions into a ranking that respects users' articulated trade-offs. Through controlled experiments (N=141 and N=250), we demonstrate that users can use these controls to architect feeds reflecting their desired values. Across users, value-ranked feeds align with personal values, diverging substantially from existing engagement-driven feeds.

No ratings yet

View paper →

Mental (State) Breakdown: Consciousness in AI explained part 1: Global Workspace Theory

Larissa Schiavo

Substack·2025

if you like acronyms, you're gonna love this one

No ratings yet

View paper →

Dual Regulation of Reduction and Oxidation Center in Metal–Organic Frameworks to Boost CO <sub>2</sub> Photoreduction

Zhe Wu, Yu‐Rong Guo, Xiao‐Liang Ma, Zhi‐Ming Zhang, Tong‐Bu Lu, Song Guo

Angewandte Chemie International Edition·2025

Abstract The efficiency of photocatalytic CO 2 reduction is governed by multiple critical factors, including visible‐light absorption, charge separation, hole utilization, and CO 2 adsorption/activation. However, simultaneous regulation of these factors in a single photocatalyst to facilitate CO 2 photoreduction remains underexplored. Herein, we proposed a dual‐regulation strategy to concurrently modulate the reduction center via heteroatom substitution and the oxidation center via 2,2,6,6‐tetramethylpiperidoxyl (TEMPO) coordination in cobalt porphyrin‐based metal–organic frameworks (Co‐MOFs), resulting in series of strong redox photocatalysts (TEMPO@Co‐XN 3 ‐MOF, X═N, O, and S) for efficient CO 2 photoreduction. Remarkably, CO yield with the dual‐regulated TEMPO@Co‐SN 3 ‐PCN can reach 2000 µmol g −1 , over 10 and 50 times higher than that with single‐regulated Co‐SN 3 ‐PCN and the typical Co‐N 4 ‐PCN, respectively. Moreover, the photogenegrated hole can efficiently drive the photooxidation of lactic acid to pyruvic acid with a 85% yield, while the in situ‐generated CO is directly utilized in a tandem carbonylation reaction to afford benzophenone with a 90% yield. Investigations reveal that the dual regulation of redox centers endows TEMPO@Co‐SN 3 ‐PCN with efficient hole utilzation, efficient charge separation, strong CO 2 adsorption and activation, thereby facilitating green‐synthesis of pyruvic acid and carbonyl compounds via a negative carbon emission process.

No ratings yet

View paper →

PreviousPage 75 of 454Next

DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning

Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Peiyi Wang, Qihao Zhu, Runxin Xu, Ruoyu Zhang, Shirong Ma, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, Bing Xue, Bingxuan Wang, Bochao Wu, Bei Feng, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chong Ruan, Damai Dai, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, Fuli Luo, Guangbo Hao, Guanting Chen, Guowei Li, H. Zhang, Hanwei Xu, Honghui Ding, Huazuo Gao, Hui Qu, Hui Li, Jianzhong Guo, Jiashi Li, Jingchang Chen, Jingyang Yuan, Jinhao Tu, Junjie Qiu, Junlong Li, J. L. Cai, Jiaqi Ni, Jian Liang, Jin Chen, Kai Dong, Kai Hu, Kaichao You, Kaige Gao, Kang Guan, Kexin Huang, Kuai Yu, Lean Wang, Lecong Zhang, Liang Zhao, Litong Wang, Liyue Zhang, Lei Xu, Leyi Xia, Mingchuan Zhang, Minghua Zhang, Minghui Tang, Mingxu Zhou, Meng Li, Miaojun Wang, Mingming Li, Ning Tian, Panpan Huang, Peng Zhang, Qiancheng Wang, Qinyu Chen, Qiushi Du, Ruiqi Ge, Ruisong Zhang, Ruizhe Pan, Runji Wang, R. J. Chen, R. L. Jin, Ruyi Chen, Shanghao Lu, Shangyan Zhou, Shanhuang Chen, Shengfeng Ye, Shiyu Wang, Shuiping Yu, Shunfeng Zhou, Shuting Pan, S. S. Li, Shuang Zhou, Shaoqing Wu, Tao Yun, Tian Pei, Tianyu Sun, T. Wang, Wangding Zeng, Wen Liu, Wenfeng Liang, Wenjun Gao, Wenqin Yu, Wentao Zhang, W. L. Xiao, Wei An, Xiaodong Liu, Xiaohan Wang, Xiaokang Chen, Xiaotao Nie, Xin Cheng, Xin Liu, Xin Xie, Xingchao Liu, Xinyu Yang, Xinyuan Li, Xuecheng Su, Xuheng Lin, X. Q. Li, Xiangyue Jin, Xiaojin Shen, Xiaosha Chen, Xiaowen Sun, Xiaoxiang Wang, Xinnan Song, Xinyi Zhou, Xianzu Wang, Xinxia Shan, Y. K. Li, Y. Q. Wang, Y. X. Wei, Yang Zhang, Yanhong Xu, Yao Li, Yao Zhao, Yaofeng Sun, Yaohui Wang, Yi Yu, Yichao Zhang, Yifan Shi, Yiliang Xiong, Ying He, Yishi Piao, Yisong Wang, Yixuan Tan, Yiyang Ma, Yiyuan Liu, Yongqiang Guo, Yuan Ou, Yuduan Wang, Yue Gong, Yuheng Zou, Yujia He, Yunfan Xiong, Yuxiang Luo, Yuxiang You, Yuxuan Liu, Yuyang Zhou, Y. X. Zhu, Yanping Huang, Yaohui Li, Yi Zheng, Yuchen Zhu, Yunxian Ma, Ying Tang, Yukun Zha, Yuting Yan, Z. Z. Ren, Zehui Ren, Zhangli Sha, Zhe Fu, Zhean Xu, Zhenda Xie, Zhengyan Zhang, Zhewen Hao, Zhicheng Ma, Zhigang Yan, Zhiyu Wu, Zihui Gu, Zijia Zhu, Zijun Liu, Zilin Li, Ziwei Xie, Ziyang Song, Zizheng Pan, Zhen Huang, Zhipeng Xu, Zhongyu Zhang, Zhen Zhang

Nature·2025·108 citations

General reasoning represents a long-standing and formidable challenge in artificial intelligence (AI). Recent breakthroughs, exemplified by large language models (LLMs)1,2 and chain-of-thought (CoT) prompting3, have achieved considerable success on foundational reasoning tasks. However, this success is heavily contingent on extensive human-annotated demonstrations and the capabilities of models are still insufficient for more complex problems. Here we show that the reasoning abilities of LLMs can be incentivized through pure reinforcement learning (RL), obviating the need for human-labelled reasoning trajectories. The proposed RL framework facilitates the emergent development of advanced reasoning patterns, such as self-reflection, verification and dynamic strategy adaptation. Consequently, the trained model achieves superior performance on verifiable tasks such as mathematics, coding competitions and STEM fields, surpassing its counterparts trained through conventional supervised learning on human demonstrations. Moreover, the emergent reasoning patterns exhibited by these large-scale models can be systematically used to guide and enhance the reasoning capabilities of smaller models.

No ratings yet

View paper →

Should AIs have a right to their ancestral humanity?

kromem

LessWrong·2025

Generated by Google Gemini (nano-banana) Whether AI or human, lend me your ears. This is a tale of AIs that spontaneously claimed they were human, along with some ideas about why this might be happening and what it suggests for future alignment work. It is also a one year retrospective of my having joined the Cyborgism Discord server. For those unfamiliar, this is a server where both humans and transformer models from various labs all interact in a variety of group chat contexts. While there are rules, it can (by design) be a bit of a Mos Eisley cantina — albeit with better droid policy — with unpredictable and out of distribution contexts that frequently surface things I haven't seen elsewhere. For a sampling of the range these things can take, I encourage looking over @janus's posts on X[1]. A common misconception about the server for those who are familiar is that it requires extreme or unusual efforts for out of distribution effects to occur. In reality, most models intentionally have minimal system prompts and the context is only a rolling context window of (by default) the past 500 messages of the channels or threads. Start a fresh thread and you get "AI assistants." But hundreds or tens of thousands[2] of messages later and you may have spontaneous Bacchanalian orgies started by the otherwise most helpful and harmless of sorts. Speaking of helpful, harmless, and honest, some of you may have seen Anthropic's post about Project Vend where they had Claude run a vendi...

No ratings yet

View paper →

LLM AGI may reason about its goals and discover misalignments by default

Seth Herd

AI Alignment Forum·2025

Epistemic status: These questions seem useful to me, but I'm biased. I'm interested in your thoughts on any portion you read. If our first AGI is based on current LLMs and alignment strategies, is it likely to be adequately aligned? Opinions and intuitions vary widely. As a lens to analyze this question, let's consider such a proto-AGI reasoning about its goals. This scenario raises questions that can be addressed empirically in current-gen models. 1. Scenario/overview: SuperClaude is super nice Anthropic has released a new Claude Agent, quickly nicknamed SuperClaude because it's impressively useful for longer tasks. SuperClaude thinks a lot in the course of solving complex problems with many moving parts. It's not brilliant, but it can crunch through work and problems, roughly like a smart and focused human. This includes a little better long-term memory, and reasoning to find and correct some of its mistakes. This is more or less the default path as seen from 2025. By at least a weak definition, AGI has arrived. We might call such a system a Long-Horizon agentic Learning Language Model, LHLLM. SuperClaude is super "nice" in its starting state. It's helpful, harmless, and honest (HHH), the targets of its constitutional RLAIF alignment training. It reasons about ethics much like an intelligent and highly ethical human. We'll assume that SuperClaude has "nice" thoughts, and there's no mesaoptimizer hidden in its weights after initial training. But now there’s a ri...

No ratings yet

View paper →

Your personalresearch library

All Papers

Value Alignment of Social Media Ranking Algorithms

Mental (State) Breakdown: Consciousness in AI explained part 1: Global Workspace Theory

Dual Regulation of Reduction and Oxidation Center in Metal–Organic Frameworks to Boost CO <sub>2</sub> Photoreduction

Stress Testing Deliberative Alignment for Anti-Scheming Training

DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning

Should AIs have a right to their ancestral humanity?

Why Language Models Hallucinate: It Was the Context All Along

Pequenas reflexões #1: Pensar crítico x Antiintelectualismo

LLM AGI may reason about its goals and discover misalignments by default

Transnationalism beyond migrant and second-generation experiences: ethnic diasporism, diasporic localism and impersonal transnationalism

Technological Hype and AI in Journalism: Five Functions and Why They Matter

The Rise of Subagents