1.5k citations · 1.7k across the 14 of their papers we have counts for
14 papers
The Dialect Tax: Dialectal Biases Persist throughout the Language Modeling Pipeline
Elle
Systematic dialectal performance gaps in language models (LMs) are well documented, but the source of these disparities within the modern language modeling pipeline remains unclear…
Toward Comprehensive Risk Assessments and Assurance of AI-Based Systems
Heidy Khlaaf
Novel safety, socio-economic, and ethical harms arising from the deployment of AI-based systems have led to a breadth of work seeking to map, measure, and mitigate against newly fo…
RTTC: Reward-Guided Collaborative Test-Time Compute
J. Pablo Muñoz, Jinjie Yuan
Test-Time Compute (TTC) has emerged as a powerful paradigm for enhancing the performance of Large Language Models (LLMs) at inference, leveraging strategies such as Test-Time Train…
A Different Approach to AI Safety: Proceedings from the Columbia Convening on Openness in Artificial Intelligence and AI Safety
Camille François, Ludovic Péran, Ayah Bdeir +17
The rapid rise of open-weight and open-source foundation models is intensifying the obligation and reshaping the opportunity to make AI systems safe. This paper reports outcomes fr…
FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and Challenging
Zichen Tang, Haihong E, Ziyan Ma +10
We introduce FinanceReasoning, a novel benchmark designed to evaluate the reasoning capabilities of large reasoning models (LRMs) in financial numerical reasoning problems. Compare…
Safety Co-Option and Compromised National Security: The Self-Fulfilling Prophecy of Weakened AI Risk Thresholds
Heidy Khlaaf, Sarah Myers West
Risk thresholds provide a measure of the level of risk exposure that a society or individual is willing to withstand, ultimately shaping how we determine the safety of technologica…
LeftoverLocals: Listening to LLM Responses Through Leaked GPU Local Memory
Tyler Sorensen, Heidy Khlaaf
This paper describes LeftoverLocals: a vulnerability that allows data recovery from GPU memory created by another process on Apple, Qualcomm, and AMD GPUs. LeftoverLocals impacts t…
A Hazard Analysis Framework for Code Synthesis Large Language Models
Heidy Khlaaf, Pamela Mishkin, Joshua Achiam +2
Codex, a large language model (LLM) trained on a variety of codebases, exceeds the previous state of the art in its capacity to synthesize and generate code. Although Codex provide…
Evaluating Large Language Models Trained on Code
Mark Chen, Jerry Tworek, Heewoo Jun +55
We introduce Codex, a GPT language model fine-tuned on publicly available code from GitHub, and study its Python code-writing capabilities. A distinct production version of Codex p…
Safety Case Templates for Autonomous Systems
Robin Bloomfield, Gareth Fletcher, Heidy Khlaaf +2
This report documents safety assurance argument templates to support the deployment and operation of autonomous systems that include machine learning (ML) components. The document…
Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims
Miles Brundage, Shahar Avin, Jasmine Wang +56
With the recent wave of progress in artificial intelligence (AI) has come a growing awareness of the large-scale impacts of AI systems, and recognition that existing regulations an…
Towards Identifying and closing Gaps in Assurance of autonomous Road vehicleS -- a collection of Technical Notes Part 2
Robin Bloomfield, Gareth Fletcher, Heidy Khlaaf +8
This report provides an introduction and overview of the Technical Topic Notes (TTNs) produced in the Towards Identifying and closing Gaps in Assurance of autonomous Road vehicleS…
Towards Identifying and closing Gaps in Assurance of autonomous Road vehicleS -- a collection of Technical Notes Part 1
Robin Bloomfield, Gareth Fletcher, Heidy Khlaaf +8
This report provides an introduction and overview of the Technical Topic Notes (TTNs) produced in the Towards Identifying and closing Gaps in Assurance of autonomous Road vehicleS…
T2: Temporal Property Verification
Marc Brockschmidt, Byron Cook, Samin Ishtiaq +2
We present the open-source tool T2, the first public release from the TERMINATOR project. T2 has been extended over the past decade to support automatic temporal-logic proving tech…