output
20032025
most citedEmergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

25 citations

9 papers

cs.SE2025★ 1 cited

ZeroFalse: Improving Precision in Static Analysis with LLMs

Mohsen Iranmanesh, Sina Moradi Sabet, Sina Marefat +4

Static Application Security Testing (SAST) tools are integral to modern software development, yet their adoption is undermined by excessive false positives that weaken developer tr…

cs.LG2025

GraphCSVAE: Graph Categorical Structured Variational Autoencoder for Spatiotemporal Auditing of Physical Vulnerability Towards Sustainable Post-Disaster Risk Reduction

Joshua Dimasaka, Christian Geiß, Robert Muir-Wood +1

In the aftermath of disasters, many institutions worldwide face challenges in monitoring changes in disaster risk, limiting assessment of progress towards the UN Sendai Framework f…

cs.CL2025★ 25 cited

Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

Jan Betley, Daniel Tan, Niels Warncke +5

We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting mode…

q-fin.PM2023

Robust Trading in a Generalized Lattice Market

Chung-Han Hsieh, Xin-Yu Wang

This paper introduces a novel robust trading paradigm, called \textit{multi-double linear policies}, situated within a \textit{generalized} lattice market. Distinctively, our frame…

quant-ph2023★ 18 cited

Quantum Monte Carlo simulations for financial risk analytics: scenario generation for equity, rate, and credit risk factors

Titos Matsakos, Stuart Nield

Monte Carlo (MC) simulations are widely used in financial risk management, from estimating value-at-risk (VaR) to pricing over-the-counter derivatives. However, they come at a sign…

stat.AP2016★ 1 cited

BNP-Seq: Bayesian Nonparametric Differential Expression Analysis of Sequencing Count Data

Siamak Zamani Dadaneh, Xiaoning Qian, Mingyuan Zhou

We perform differential expression analysis of high-throughput sequencing count data under a Bayesian nonparametric framework, removing sophisticated ad-hoc pre-processing steps co…

stat.ME2015

A deconvolution path for mixtures

Oscar Hernan Madrid Padilla, Nicholas G. Polson, James G. Scott

We propose a class of estimators for deconvolution in mixture models based on a simple two-step "bin-and-smooth" procedure applied to histogram counts. The method is both statistic…

stat.ME2014★ 1 cited

Decoupling shrinkage and selection in Bayesian linear models: a posterior summary perspective

P. Richard Hahn, Carlos M. Carvalho

Selecting a subset of variables for linear models remains an active area of research. This paper reviews many of the recent contributions to the Bayesian model selection and shrink…

physics.ao-ph2003★ 25 cited

A New Framework for the Assessment and Calibration of Medium Range Ensemble Temperature Forecasts

Stephen Jewson, Anders Brix, Christine Ziehmann

We present a new framework for the assessment and calibration of medium range ensemble temperature forecasts. The method is based on maximising the likelihood of a simple parametri…