paper-with-me

Papers

Neural Interactive Proofs

2024-12-12 · Lewis Hammond, Sam Adam-Day

We consider the problem of how a trusted, but computationally bounded agent (a 'verifier') can learn to interact with one or more powerful but untrusted agents ('provers') in order to solve a given task. More specifically, we study the case in which agents are represented using neural networks and refer to solutions of this problem as neural interactive proofs. First we introduce a unifying framework based on prover-verifier games, which generalises previously proposed interaction protocols. We then describe several new protocols for generating neural interactive proofs, and provide a theoretical comparison of both new and existing approaches. Finally, we support this theory with experiments in two domains: a toy graph isomorphism problem that illustrates the key ideas, and a code validation task using large language models. In so doing, we aim to create a foundation for future work on neural interactive proofs and their application in building safer AI systems.

📄 PDF Abstract BibTeX arXiv:2412.08897

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

How to Avoid Debate: Scalable AI Safety via Doubly-Efficient Interactive Proofs

2026-07-03 · Liyan Chen, Yael Tauman Kalai, Zoe Xi arxiv

As AI models continue to develop powerful capabilities, it becomes critical that we are able to verify that their output is aligned with our intentions. A recent line of work focuses on verification via debate, a model o…

Evonne: Interactive Proof Visualization for Description Logics (System Description) -- Extended Version

2022-05-19 · Christian Alrabbaa, Franz Baader, Stefan Borgwardt, Raimund Dachselt 외

Explanations for description logic (DL) entailments provide important support for the maintenance of large ontologies. The "justifications" usually employed for this purpose in ontology editors pinpoint the parts of the …

Towards Autoformalization of Mathematics and Code Correctness: Experiments with Elementary Proofs

2023-01-05 · Garett Cunningham, Razvan C. Bunescu, David Juedes

The ever-growing complexity of mathematical proofs makes their manual verification by mathematicians very cognitively demanding. Autoformalization seeks to address this by translating proofs written in natural language i…

Mathematical ProofsSemantic Parsing

Recycling Proof Patterns in Coq: Case Studies

2013-01-25 · Jónathan Heras, Ekaterina Komendantskaya

Development of Interactive Theorem Provers has led to the creation of big libraries and varied infrastructures for formal proofs. However, despite (or perhaps due to) their sophistication, the re-use of libraries by non-…

BIG-bench Machine Learning

Towards Automated Readable Proofs of Ruler and Compass Constructions

2024-01-22 · Vesna Marinković, Tijana Šukilović, Filip Marić

Although there are several systems that successfully generate construction steps for ruler and compass construction problems, none of them provides readable synthetic correctness proofs for generated constructions. In th…