5 citations · 12 across the 4 of their papers we have counts for
5 papers
Agentic Backdoors via Pretraining Poisoning
Xinyan Hu, Pingbang Hu, Chloe Loughridge +5
Large language models are pretrained on vast, uncurated corpora scraped from the public web. This creates a security risk from attackers who plant poisoned content in the pretraini…
dafny-annotator: AI-Assisted Verification of Dafny Programs
Gabriel Poesia, Chloe Loughridge, Nada Amin
Formal verification has the potential to drastically reduce software bugs, but its high additional cost has hindered large-scale adoption. While Dafny presents a promise to signifi…
DafnyBench: A Benchmark for Formal Software Verification
Chloe Loughridge, Qinyi Sun, Seth Ahrenbach +7
We introduce DafnyBench, the largest benchmark of its kind for training and evaluating machine learning systems for formal software verification. We test the ability of LLMs such a…
Opening the AI black box: program synthesis via mechanistic interpretability
Eric J. Michaud, Isaac Liao, Vedang Lad +7
We present MIPS, a novel method for program synthesis based on automated mechanistic interpretability of neural networks trained to perform the desired task, auto-distilling the le…
VerMCTS: Synthesizing Multi-Step Programs using a Verifier, a Large Language Model, and Tree Search
David Brandfonbrener, Simon Henniger, Sibi Raja +8
Large Language Models (LLMs) can generate useful code, but often the code they generate cannot be trusted to be sound. In this paper, we present VerMCTS, an approach to begin to re…