activity
20102025
most citedConstitutional AI: Harmlessness from AI Feedback

334 citations · 2.9k across the 27 of their papers we have counts for

collaborators

27 papers

cs.LG2025★ 2 cited

Sleepless Nights, Sugary Days: Creating Synthetic Users with Health Conditions for Realistic Coaching Agent Interactions

Taedong Yun, Eric Yang, Mustafa Safdari +13

We present an end-to-end framework for generating synthetic users for evaluating interactive agents designed to encourage positive behavior changes, such as in health and lifestyle…

hep-ph2024★ 1 cited

Orbital Dynamics of the Solar Basin

Cara Giovanetti, Robert Lasenby, Ken Van Tilburg

We study the dynamics of the solar basin -- the accumulated population of weakly-interacting particles on bound orbits in the Solar System. We focus on particles starting off on Su…

cs.CL2023★ 53 cited

The Capacity for Moral Self-Correction in Large Language Models

Deep Ganguli, Amanda Askell, Nicholas Schiefer +46

We test the hypothesis that language models trained with reinforcement learning from human feedback (RLHF) have the capability to "morally self-correct" -- to avoid producing harmf…

cs.CL2022★ 334 cited

Constitutional AI: Harmlessness from AI Feedback

Yuntao Bai, Saurav Kadavath, Sandipan Kundu +48

As AI systems become more capable, we would like to enlist their help to supervise other AIs. We experiment with methods for training a harmless AI assistant through self-improveme…

cs.LG2022★ 48 cited

Toy Models of Superposition

Nelson Elhage, Tristan Hume, Catherine Olsson +13

Neural networks often pack many unrelated concepts into a single neuron - a puzzling phenomenon known as 'polysemanticity' which makes interpretability much more challenging. This…

hep-ph2022★ 1 cited

Dark matter scattering in astrophysical media: collective effects

William DeRocco, Marios Galanis, Robert Lasenby

It is well-known that stars have the potential to be excellent dark matter detectors. Infalling dark matter that scatters within stars could lead to a range of observational signat…

hep-ph2021★ 14 cited

DM-electron scattering in materials: sum rules and heterostructures

Robert Lasenby, Anirudh Prabhu

In recent years, a growing experimental program has begun to search for sub-GeV dark matter through its scattering with electrons. An associated theoretical challenge is to compute…

hep-ex2021★ 160 cited

New Constraints on Dark Photon Dark Matter with Superconducting Nanowire Detectors in an Optical Haloscope

Jeff Chiles, Ilya Charaev, Robert Lasenby +9

Uncovering the nature of dark matter is one of the most important goals of particle physics. Light bosonic particles, such as the dark photon, are well-motivated candidates: they a…

quant-ph2021★ 15 cited

New bounds on adaptive quantum metrology under Markovian noise

Kianna Wan, Robert Lasenby

We analyse the problem of estimating a scalar parameter that controls the Hamiltonian of a quantum system subject to Markovian noise. Specifically, we place bounds on the growt…

hep-ph2020★ 231 cited

Black hole superradiance of self-interacting scalar fields

Masha Baryakhtar, Marios Galanis, Robert Lasenby +1

Black hole superradiance is a powerful probe of light, weakly-coupled hidden sector particles. Many candidate particles, such as axions, generically have self-interactions that can…

hep-ph2020★ 29 cited

Dark Photons in the Solar Basin

Robert Lasenby, Ken Van Tilburg

Production of dark photons inside the Sun forms the basis for the most sensitive probes of such particles over a wide mass range. A small fraction of dark photons is emitted into g…

hep-ph2020★ 25 cited

Long range dark matter self-interactions and plasma instabilities

Robert Lasenby

So far, the observed effects of dark matter are compatible with it having purely gravitational interactions. However, in many models, dark matter has additional interactions with i…

hep-ph2019★ 25 cited

Parametrics of electromagnetic searches for axion dark matter

Robert Lasenby

Light axion-like particles occur in many theories of beyond-Standard-Model physics, and may make up some or all of the universe's dark matter. One of the ways they can couple to th…

hep-ph2019★ 47 cited

Microwave cavity searches for low-frequency axion dark matter

Robert Lasenby

For low-mass (frequency GHz) axions, dark matter detection experiments searching for an axion-photon-photon coupling generally have suppressed sensitivity, if they use a stat…

hep-ph2018★ 30 cited

Light vectors coupled to bosonic currents

Jeff A. Dror, Robert Lasenby, Maxim Pospelov

New spin-1 particles with masses below the weak scale are present in many theories of beyond Standard Model (SM) physics. In this work, we extend previous analyses by systematicall…

hep-ph2018★ 194 cited

Axion and hidden photon dark matter detection with multilayer optical haloscopes

Masha Baryakhtar, Junwu Huang, Robert Lasenby

A well-motivated class of dark matter candidates, including axions and dark photons, takes the form of coherent oscillations of a light bosonic field. If the dark matter couples to…

hep-ph2017★ 166 cited

Dark forces coupled to non-conserved currents

Jeff A. Dror, Robert Lasenby, Maxim Pospelov

New light vectors with dimension-4 couplings to Standard Model states have (energy / vector mass)^2 enhanced production rates unless the current they couple to is conserved. These…

hep-ph2017★ 169 cited

New constraints on light vectors coupled to anomalous currents

Jeff A. Dror, Robert Lasenby, Maxim Pospelov

We derive new constraints on light vectors coupled to Standard Model (SM) fermions, when the corresponding SM current is broken by the chiral anomaly. Cancellation of the anomaly b…

hep-ph2017★ 300 cited

Black Hole Superradiance Signatures of Ultralight Vectors

Masha Baryakhtar, Robert Lasenby, Mae Teo

The process of superradiance can extract angular momentum and energy from astrophysical black holes (BHs) to populate gravitationally-bound states with an exponentially large numbe…

hep-ph2016★ 319 cited

Stellar cooling bounds on new light particles: plasma mixing effects

Edward Hardy, Robert Lasenby

Strong constraints on the coupling of new light particles to the Standard Model (SM) arise from their production in the hot cores of stars, and the effects of this on stellar cooli…

hep-ph2016★ 260 cited

Black Hole Mergers and the QCD Axion at Advanced LIGO

Asimina Arvanitaki, Masha Baryakhtar, Savas Dimopoulos +2

In the next few years Advanced LIGO (aLIGO) may see gravitational waves (GWs) from thousands of black hole (BH) mergers. This marks the beginning of a new precision tool for physic…

hep-ph2015★ 64 cited

Signatures of Large Composite Dark Matter States

Edward Hardy, Robert Lasenby, John March-Russell +1

We investigate the interactions of large composite dark matter (DM) states with the Standard Model (SM) sector. Elastic scattering with SM nuclei can be coherently enhanced by fact…

hep-ph2015★ 111 cited

Twin Higgs Asymmetric Dark Matter

Isabel García García, Robert Lasenby, John March-Russell

We study Asymmetric Dark Matter (ADM) in the context of the minimal (Fraternal) Twin Higgs solution to the little hierarchy problem, with a twin sector with gauged $SU(3)' \times S…

hep-ph2015★ 113 cited

Twin Higgs WIMP Dark Matter

Isabel García García, Robert Lasenby, John March-Russell

Dark matter (DM) without a matter asymmetry is studied in the context of Twin Higgs (TH) theories in which the LHC naturalness problem is addressed. These possess a twin sector rel…