English
Related papers

Related papers: NP-Hard Lower Bound Complexity for Semantic Self-V…

200 papers

Much of the recent work developing formal methods techniques to specify or learn the behavior of autonomous systems is predicated on a belief that formal specifications are interpretable and useful for humans when checking systems. Though…

Artificial Intelligence · Computer Science 2023-05-30 Ho Chit Siu , Kevin Leahy , Makai Mann

Automated grading systems can efficiently score short-answer responses, yet they often fail to indicate when a grading decision is uncertain or potentially contentious. We introduce semantic entropy, a measure of variability across multiple…

Artificial Intelligence · Computer Science 2025-08-07 Karrtik Iyer , Manikandan Ravikiran , Prasanna Pendse , Shayan Mohanty

Automating the translation of natural-language specifications into logic programs is a challenging task that affects neurosymbolic engineering. We present ASP-Bench, a benchmark comprising 128 natural language problem instances, 64 base…

Artificial Intelligence · Computer Science 2026-02-03 Stefan Szeider

Random constraint satisfaction problems (CSPs) such as random $3$-SAT are conjectured to be computationally intractable. The average case hardness of random $3$-SAT and other CSPs has broad and far-reaching implications on problems in…

Computational Complexity · Computer Science 2019-11-11 Jonah Brown-Cohen , Prasad Raghavendra

Sparse Autoencoders (SAEs) that can accurately reconstruct their input (minimizing distortion) by making efficient use of few features (minimizing the rate) often fail to learn monosemantic representations (highly interpretable), limiting…

Machine Learning · Computer Science 2026-05-15 Tommaso Mencattini , Francesco Montagna , Francesco Locatello

Automatic evaluation remains an open research question in Natural Language Generation. In the context of Sentence Simplification, this is particularly challenging: the task requires by nature to replace complex words with simpler ones that…

Computation and Language · Computer Science 2021-04-19 Thomas Scialom , Louis Martin , Jacopo Staiano , Éric Villemonte de la Clergerie , Benoît Sagot

Self-improvement at scale has been a longstanding goal for reasoning models, and there are two natural places to do it: at test time, through verification-refinement (V-R) loops; and at training time, through self-training methods. Both are…

Machine Learning · Computer Science 2026-05-29 Chen Henry Wu , Aditi Raghunathan

We build a SAT solver implementing the DPLL algorithm in the verification-enabled programming language Dafny. The resulting solver is fully verified (soundness, completeness and termination are computer checked). We benchmark our Dafny…

Logic in Computer Science · Computer Science 2020-07-22 Cezar-Constantin Andrici , Ştefan Ciobâcă

Trustworthy capability evaluations are crucial for ensuring the safety of AI systems, and are becoming a key component of AI regulation. However, the developers of an AI system, or the AI system itself, may have incentives for evaluations…

Artificial Intelligence · Computer Science 2025-02-10 Teun van der Weij , Felix Hofstätter , Ollie Jaffe , Samuel F. Brown , Francis Rhys Ward

We present a novel neural architecture for the Argument Reasoning Comprehension task of SemEval 2018. It is a simple neural network consisting of three parts, collectively judging whether the logic built on a set of given sentences (a…

Computation and Language · Computer Science 2018-05-21 Taeuk Kim , Jihun Choi , Sang-goo Lee

Verifying that input-output relationships of a neural network conform to prescribed operational specifications is a key enabler towards deploying these networks in safety-critical applications. Semidefinite programming (SDP)-based…

Optimization and Control · Mathematics 2022-03-08 Robin Brown , Edward Schmerling , Navid Azizan , Marco Pavone

Verifying robustness of neural networks given a specified threat model is a fundamental yet challenging task. While current verification methods mainly focus on the $\ell_p$-norm threat model of the input instances, robustness verification…

Machine Learning · Computer Science 2020-06-16 Jeet Mohapatra , Tsui-Wei , Weng , Pin-Yu Chen , Sijia Liu , Luca Daniel

Recently, the separated fragment (SF) has been introduced and proved to be decidable. Its defining principle is that universally and existentially quantified variables may not occur together in atoms. The known upper bound on the time…

Logic in Computer Science · Computer Science 2017-04-10 Marco Voigt

Many fundamental problems in artificial intelligence, knowledge representation, and verification involve reasoning about sets and relations between sets and can be modeled as set constraint satisfaction problems (set CSPs). Such problems…

Artificial Intelligence · Computer Science 2012-07-19 Manuel Bodirsky , Martin Hils , Alex Krimkevich

Reliable verification of proofs remains a bottleneck for training and evaluating AI systems on hard mathematical reasoning. Fully formal proofs, in languages like Lean, are easy to verify because they are unambiguous and modular. Most…

Logic in Computer Science · Computer Science 2026-05-21 Slim Barkallah , Luke Bailey , Kaiyue Wen , Mohammed Abouzaid , Tengyu Ma

This paper shows effectiveness of X3SAT in proving P = NP. This is due to the fact that it is easy to check unsatisfiability of a particular truth assignment. A truth assignment leads to some reductions of clauses by means of "exactly-1…

Computational Complexity · Computer Science 2020-04-08 Latif Salum

Semidefinite programming (SDP) relaxation has emerged as a promising approach for neural network verification, offering tighter bounds than other convex relaxation methods for deep neural networks (DNNs) with ReLU activations. However, we…

Machine Learning · Computer Science 2025-06-13 Ryota Ueda , Takami Sato , Ken Kobayashi , Kazuhide Nakata

Despite the syntactic fluency of Large Language Models (LLMs), ensuring their logical correctness in high-stakes domains remains a fundamental challenge. We present a neurosymbolic framework that combines LLMs with SMT solvers to produce…

Computation and Language · Computer Science 2026-05-05 Vikash Singh , Darion Cassel , Nathaniel Weir , Nick Feng , Sam Bayless

The global Lipschitz constant of a neural network is related to robustness and generalization, yet unlike in many classical models, it is not plainly legible from the parameters. This has motivated sophisticated verification algorithms,…

Machine Learning · Computer Science 2026-05-11 Simon Kuang , Yuezhu Xu , S. Sivaranjani , Xinfan Lin

The Subset Sum problem is a classical NP-complete problem with a long-standing $O^*(2^{n/2})$ deterministic bound due to Horowitz and Sahni. We present results at two distinct levels of generality. First (instance-sensitive bound), we…

Computational Complexity · Computer Science 2025-08-29 Jesus Salas