About

Jennifer Chayes is the Dean of the College of Computing, Data Science, and Society at the University of California Berkeley. She holds professorships in EECS, Mathematics, Statistics, and the School of Information. Prior to her tenure at Berkeley, she was at Microsoft for over 20 years, where she served as Technical Fellow and founded and managed three interdisciplinary labs: Microsoft Research New England, New York City, and Montreal. Her research areas include phase transitions in computer science, structural and dynamical properties of networks, modeling and graph algorithms, and the development of graphons, which are widely used in machine learning of large-scale networks. Her recent work focuses on machine learning, with applications in cancer immunotherapy, ethical decision-making, and climate change. Chayes has received numerous awards for leadership and scientific contributions, including the Anita Borg Institute Women of Vision Leadership Award, the John von Neumann Award from the Society for Industrial and Applied Mathematics, and an honorary doctorate from Leiden University. She is a member of the American Academy of Arts and Sciences and the National Academy of Sciences.

Research topics

• Computer Science
• Combinatorics
• Information Retrieval
• Political Science
• Chemistry
• Artificial Intelligence
• Data science
• Mathematics
• Statistics
• Algorithm
• Medicine
• Engineering
• Biochemistry
• Organic chemistry
• Physics
• Database
• Anatomy
• Discrete mathematics
• Statistical physics
• Programming language

Selected publications

• Synthesis of Highly Crystalline Covalent Organic Frameworks Using Large Language Models

  Journal of the American Chemical Society · 2026-02-23 · 5 citations

  article

  Crystallizing covalent organic frameworks (COFs) remain a central challenge in reticular chemistry, as achieving long-range order typically requires extensive trial-and-error optimization over many months or years. Here, we demonstrate that by integrating a deep research agent within ChatGPT, this process can be markedly accelerated, reducing the crystallization timeline to less than one month. Our approach, termed the LLM For Accelerated Synthesis Technique (LFAST), operates through two interlinked cycles. In the first, we formulated a structured, multistep prompt to guide the deep research agent in mining, correlating, and validating synthesis parameters from the relevant chemical literature. This yielded an expanded and refined design space for reaction condition screening. In the second, these conditions were executed by using an automated synthesis platform coupled with high-throughput powder X-ray diffraction analysis. Using a widely reported β-ketoenamine-linked COF, TpPa-SO3H, as a benchmark, LFAST produced frameworks with diffraction peaks corresponding to a 350% increase in crystallinity index (CI) relative to prior reports. The same protocol enabled the synthesis of an unreported β-ketoenamine-linked COF-2000 with an even higher structural order. To ensure reproducibility and data accessibility, we further introduce a standardized metadata format encompassing synthesis and PXRD data sets. This data-driven methodology transforms the way that COFs are crystallized and significantly accelerates the pace of materials discovery.

  PublisherDOI

• MOFGen database

  Zenodo (CERN European Organization for Nuclear Research) · 2026-02-02

  datasetOpen access
  PublisherDOI

• Auditing the Auditors: Does Community-based Moderation Get It Right?

  arXiv (Cornell University) · 2026-03-17

  preprintOpen accessSenior author

  Online social platforms increasingly rely on crowd-sourced systems to label misleading content at scale, but these systems must both aggregate users' evaluations and decide whose evaluations to trust. To address the latter, many platforms audit users by rewarding agreement with the final aggregate outcome, a design we term consensus-based auditing. We analyze the consequences of this design in X's Community Notes, which in September 2022 adopted consensus-based auditing that ties users' eligibility for participation to agreement with the eventual platform outcome. We find evidence of strategic conformity: minority contributors' evaluations drift toward the majority and their participation share falls on controversial topics, where independent signals matter most. We formalize this mechanism in a behavioral model in which contributors trade off private beliefs against anticipated penalties for disagreement. Motivated by these findings, we propose a two-stage auditing and aggregation algorithm that weights contributors by the stability of their past residuals rather than by agreement with the majority. The method first accounts for differences across content and contributors, and then measures how predictable each contributor's evaluations are relative to the latent-factor model. Contributors whose evaluations are consistently informative receive greater influence in aggregation, even when they disagree with the prevailing consensus. In the Community Notes data, this approach improves out-of-sample predictive performance while avoiding penalization of disagreement.

  PublisherDOI

• Auditing the Auditors: Does Community-based Moderation Get It Right?

  ArXiv.org · 2026-03-17

  articleOpen accessSenior author

  Online social platforms increasingly rely on crowd-sourced systems to label misleading content at scale, but these systems must both aggregate users' evaluations and decide whose evaluations to trust. To address the latter, many platforms audit users by rewarding agreement with the final aggregate outcome, a design we term consensus-based auditing. We analyze the consequences of this design in X's Community Notes, which in September 2022 adopted consensus-based auditing that ties users' eligibility for participation to agreement with the eventual platform outcome. We find evidence of strategic conformity: minority contributors' evaluations drift toward the majority and their participation share falls on controversial topics, where independent signals matter most. We formalize this mechanism in a behavioral model in which contributors trade off private beliefs against anticipated penalties for disagreement. Motivated by these findings, we propose a two-stage auditing and aggregation algorithm that weights contributors by the stability of their past residuals rather than by agreement with the majority. The method first accounts for differences across content and contributors, and then measures how predictable each contributor's evaluations are relative to the latent-factor model. Contributors whose evaluations are consistently informative receive greater influence in aggregation, even when they disagree with the prevailing consensus. In the Community Notes data, this approach improves out-of-sample predictive performance while avoiding penalization of disagreement.

  PublisherOA PDF

• MOFGen database

  Zenodo (CERN European Organization for Nuclear Research) · 2026-02-02

  datasetOpen access
  PublisherDOI

• An automated evaluation agent for Q&A pairs and reticular synthesis conditions

  Digital Discovery · 2025-11-18

  articleOpen accessCorresponding

  QAutoEval is an automated evaluation agent for Q&A datasets and reticular synthesis conditions, enabling reproducible benchmarking and transparent assessment of LLM driven workflows in reticular chemistry.

  PublisherOA PDFDOI

• Advancing science- and evidence-based AI policy

  Science · 2025-07-31 · 10 citations

  articleOpen access

  Policy must be informed by, but also facilitate the generation of, scientific evidence.

  PublisherOA PDFDOI

• Comparison of LLMs in extracting synthesis conditions and generating Q&A datasets for metal–organic frameworks

  Digital Discovery · 2025-01-01 · 11 citations

  articleOpen access

  Spoiler alert: Claude and Gemini did better than GPT-4 in extracting information from chemistry literature.

  PublisherOA PDFDOI

• Pinpointing the Onset of Water Harvesting in Reticular Frameworks from Structure

  ACS Central Science · 2025-02-17 · 15 citations

  articleOpen access

  Covalent organic frameworks (COFs) have emerged as promising atmospheric water harvesters, offering a potential solution to the pressing global issue of water scarcity, which threatens millions of lives worldwide. This study presents a series of 2D COFs, including HCOF-3, HCOF-2, and a newly developed structure named COF-309, designed for optimized water harvesting performance with a high working capacity at low relative humidity. To elucidate their water sorption behavior, we introduce a hydrophilicity index directly linked to intrinsic properties, such as the strength and spatial density of adsorptive sites. This index is mathematically correlated to the step of water adsorption isotherms. Our correlation provides a predictive tool that extends to other microporous COFs and metal-organic frameworks, significantly enhancing the ability to predict their onset positions of water adsorption isotherms based on structural characteristics. This advancement holds the potential to guide the development of more efficient materials for atmospheric water harvesting.

  PublisherDOI

• Algorithmic iterative reticular synthesis of zeolitic imidazolate framework crystals

  Nature Synthesis · 2025-11-25 · 7 citations

  articleOpen access

  Abstract The discovery of crystalline reticular materials remains largely trial-and-error despite their societal importance. We introduce our algorithmic iterative reticular synthesis (AIRES) cycle, which integrates automated synthesis, image recognition, single-crystal X-ray diffraction and, crucially, customized algorithmic decision-making, to maximize distinct crystal discoveries rather than optimizing single targets. Demonstrated on zeolitic imidazolate frameworks (ZIFs), AIRES achieves twice the discovery rate of random exploration, crystallizing 10 new linkers into diverse ZIF topologies and expanding the single-linker Zn-ZIF library by one-third. By transforming reticular synthesis from an empirical process to a systematic exploration, AIRES provides a scalable and efficient blueprint for accelerating materials discovery.

  PublisherOA PDFDOI

Recent grants

• BD Hubs: Collaborative Proposal: West: Accelerating the Big Data Innovation Ecosystem

  NSF · $2.8M · 2019–2024

Frequent coauthors

• Christian Borgs

  381 shared

• L. Chayes

  University of California, Los Angeles

  50 shared

• Omar M. Yaghi

  King Abdulaziz City for Science and Technology

  45 shared

• Béla Bollobás

  43 shared

• Oliver Riordan

  39 shared

• Riccardo Zecchina

  31 shared

• Nakul Rampal

  Kavli Energy NanoScience Institute

  30 shared

• László Lovász

  Alfréd Rényi Institute of Mathematics

  29 shared

Education

• Ph.D., Physics

  Princeton University

  1983

• B.A., Physics and Biology

  Wesleyan University

  1979

Awards & honors

• Anita Borg Institute Women of Vision Leadership Award
• John von Neumann Award of the Society for Industrial and App…
• honorary doctorate from Leiden University
• member of the American Academy of Arts and Sciences
• member of the National Academy of Sciences