arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.08630cs.AIcs.CC
收藏

与时间高效地进行辩论

Debate is efficient with your time

Google DeepMind(谷歌DeepMind);UK AI Security Institute(英国人工智能安全研究所);University of Haifa(海法大学);Rutgers University(罗格斯大学)

Jonah Brown-Cohen, Geoffrey Irving, Simon C. Marshall, Ilan Newman, Georgios Piliouras, Mario Szegedy

AI总结:

通过辩论实现人工智能安全,证明辩论查询复杂度与电路复杂性密切相关。

摘要:

通过辩论实现人工智能安全利用两个竞争模型来帮助人类判断者验证复杂计算任务。先前的工作已经确立了辩论在原则上可以解决哪些问题,但尚未分析人类监督的实际成本:判断者必须对辩论记录做出多少次查询?我们引入了辩论查询复杂度(DQC),即验证者必须检查的最少位数以正确决定辩论。出人意料的是,我们发现PSPACE/poly(辩论可以高效决定的问题类别)恰好是可以通过O(log n)次查询决定的函数类别。这一特征表明,辩论在查询效率上非常突出:即使对于高度复杂的问题,仅需对数级的监督也足够。我们还证明了依赖所有输入位的函数需要Omega(log n)次查询,并且任何可通过大小为s的电路计算的函数满足DQC(f) <= log(s) + 3。有趣的是,这一结果意味着证明DQC下界为log(n) + 6对于P中的语言将产生新的电路下界,将辩论查询复杂度与电路复杂性中的核心问题联系起来。

英文摘要:

AI safety via debate uses two competing models to help a human judge verify complex computational tasks. Previous work has established what problems debate can solve in principle, but has not analysed the practical cost of human oversight: how many queries must the judge make to the debate transcript? We introduce Debate Query Complexity}(DQC), the minimum number of bits a verifier must inspect to correctly decide a debate. Surprisingly, we find that PSPACE/poly (the class of problems which debate can efficiently decide) is precisely the class of functions decidable with O(log n) queries. This characterisation shows that debate is remarkably query-efficient: even for highly complex problems, logarithmic oversight suffices. We also establish that functions depending on all their input bits require Omega(log n) queries, and that any function computable by a circuit of size s satisfies DQC(f) <= log(s) + 3. Interestingly, this last result implies that proving DQC lower bounds of log(n) + 6 for languages in P would yield new circuit lower bounds, connecting debate query complexity to central questions in circuit complexity.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑