Zobrazeno 1 - 10
of 382
pro vyhledávání: '"Alur, Rajeev"'
We study how to subvert large language models (LLMs) from following prompt-specified rules. We model rule-following as inference in propositional Horn logic, a mathematical system in which rules have the form ``if $P$ and $Q$, then $R$'' for some pro
Externí odkaz:
http://arxiv.org/abs/2407.00075
Autor:
Solko-Breslin, Alaia, Choi, Seewon, Li, Ziyang, Velingker, Neelay, Alur, Rajeev, Naik, Mayur, Wong, Eric
Many computational tasks can be naturally expressed as a composition of a DNN followed by a program written in a traditional programming language or an API call to an LLM. We call such composites "neural programs" and focus on the problem of learning
Externí odkaz:
http://arxiv.org/abs/2406.06246
While automated vulnerability detection techniques have made promising progress in detecting security vulnerabilities, their scalability and applicability remain challenging. The remarkable performance of Large Language Models (LLMs), such as GPT-4 a
Externí odkaz:
http://arxiv.org/abs/2311.16169
Explanation methods for machine learning models tend not to provide any formal guarantees and may not reflect the underlying decision-making process. In this work, we analyze stability as a property for reliable feature attribution methods. We prove
Externí odkaz:
http://arxiv.org/abs/2307.05902
Autor:
Alur, Rajeev, Bastani, Osbert, Jothimurugan, Kishor, Perez, Mateo, Somenzi, Fabio, Trivedi, Ashutosh
The difficulty of manually specifying reward functions has led to an interest in using linear temporal logic (LTL) to express objectives for reinforcement learning (RL). However, LTL has the downside that it is sensitive to small perturbations in the
Externí odkaz:
http://arxiv.org/abs/2305.17115
Publikováno v:
Proceedings of the 40th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023
Compositional reinforcement learning is a promising approach for training policies to perform complex long-horizon tasks. Typically, a high-level task is decomposed into a sequence of subtasks and a separate policy is trained to perform each subtask.
Externí odkaz:
http://arxiv.org/abs/2302.02984
Streaming string transducers (SSTs) implement string-to-string transformations by reading each input word in a single left-to-right pass while maintaining fragments of potential outputs in a finite set of string variables. These variables get updated
Externí odkaz:
http://arxiv.org/abs/2209.05448
Neural networks are central to many emerging technologies, but verifying their correctness remains a major challenge. It is known that network outputs can be sensitive and fragile to even small input perturbations, thereby increasing the risk of unpr
Externí odkaz:
http://arxiv.org/abs/2206.03482
Reinforcement learning has been shown to be an effective strategy for automatically training policies for challenging control problems. Focusing on non-cooperative multi-agent systems, we propose a novel reinforcement learning framework for training
Externí odkaz:
http://arxiv.org/abs/2206.03348