Search Results for author:
Found 26 papers, 6 papers with code
Aligning Multidimensional Worldviews and Discovering Ideological Differences
The Internet is home to thousands of communities, each with their own unique worldview and associated ideological differences.
LLM Social Simulations Are a Promising Research Method
Accurate and verifiable large language model (LLM) simulations of human research subjects promise an accessible data source for understanding human behavior and training new AI systems.
Research on Superalignment Should Advance Now with Parallel Optimization of Competence and Conformity
The recent leap in AI capabilities, driven by big generative models, has sparked the possibility of achieving Artificial General Intelligence (AGI) and further triggered discussions on Artificial Superintelligence (ASI), a system surpassing all humans across all domains.
Linear Representations of Political Perspective Emerge in Large Language Models
This paper studies how LLMs are seemingly able to reflect more liberal versus more conservative viewpoints among other political perspectives in American politics.
Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voters
Through a voting simulation, we first demonstrate 18 open- and closed-weight LLMs' political preference for a Democratic nominee over a Republican nominee.
Designing LLM-Agents with Personalities: A Psychometric Approach
This research introduces a novel methodology for assigning quantifiable, controllable and psychometrically validated personalities to Large Language Models-Based Agents (Agents) using the Big Five personality framework.
Computational Life: How Well-formed, Self-replicating Programs Emerge from Simple Interaction
The fields of Origin of Life and Artificial Life both question what life is and how it emerges from a distinct set of "pre-life" dynamics.
China's Rising Leadership in Global Science
Major shifts in the global system of science and technology are destabilizing the global status order and demonstrating the capacity for emerging countries like China and India to exert greater influence.
Modularity, Higher-Order Recombination, and New Venture Success
Modularity is critical for the emergence and evolution of complex social, natural, and technological systems robust to exploratory failure.
Evolving AI Collectives to Enhance Human Diversity and Enable Self-Regulation
Large language model behavior is shaped by the language of those with whom they interact.
Can Large Language Model Agents Simulate Human Trust Behavior?
In this paper, we focus on one critical and elemental behavior in human interactions, trust, and investigate whether LLM agents can simulate human trust behavior.
The Future of Fundamental Science Led by Generative Closed-Loop Artificial Intelligence
Yet, AI has contributed less to fundamental science in part because large data sets of high-quality data for scientific practice and model discovery are more difficult to access.
Accelerating science with human-aware artificial intelligence
Artificial intelligence (AI) models trained on published scientific findings have been used to invent valuable materials and targeted therapies, but they typically ignore the human scientists who continually alter the landscape of discovery.
Complementary artificial intelligence designed to augment human discovery
When we evaluate the promise of our predictions with first-principles equations, we demonstrate that increased complementarity of our predictions does not decrease and in some cases increases the probability that the predictions possess the targeted properties.
Semantic maps and metrics for science Semantic maps and metrics for science using deep transformer encoders
Finally, with the goal of leveraging contextual representations from deep encoders, we present a range of measurements for understanding and forecasting research communities in science.
Accelerating science with human versus alien artificial intelligences
These AI approaches typically ignore the distribution of human prediction engines -- scientists and inventor -- who continuously alter the landscape of discovery and invention.
Information Lattice Learning
ILL focuses on explainability and generalizability from "small data", and aims for rules akin to those humans distill from experience (rather than a representation optimized for a specific task like classification).
Long-range Event-level Prediction and Response Simulation for Urban Crime and Global Terrorism with Granger Networks
Large-scale trends in urban crime and global terrorism are well-predicted by socio-economic drivers, but focused, event-level predictions have had limited success.
Science and Technology Advance through Surprise
Breakthrough discoveries and inventions involve unexpected combinations of contents including problems, methods, and natural entities, and also diverse contexts such as journals, subfields, and conferences.
Wasserstein Soft Label Propagation on Hypergraphs: Algorithm and Generalization Error Bounds
Inspired by recent interests of developing machine learning and data mining algorithms on hypergraphs, we investigate in this paper the semi-supervised learning algorithm of propagating "soft labels" (e. g. probability distributions, class membership scores) over hypergraphs, by means of optimal transportation.
Curvature of Hypergraphs via Multi-Marginal Optimal Transport
We introduce a novel definition of curvature for hypergraphs, a natural generalization of graphs, by introducing a multi-marginal optimal transport problem for a naturally defined random walk on the hypergraph.
Adaptive Sampling for Coarse Ranking
We consider the problem of active coarse ranking, where the goal is to sort items according to their means into clusters of pre-specified sizes, by adaptively sampling from their reward distributions.
The Wisdom of Polarized Crowds
Our analysis then reveals that polarized teams---those consisting of a balanced set of politically diverse editors---create articles of higher quality than politically homogeneous teams.
Fast, Flexible Models for Discovering Topic Correlation across Weakly-Related Collections
Weak topic correlation across document collections with different numbers of topics in individual collections presents challenges for existing cross-collection topic models.
