English
Related papers

Related papers: Improving LLM Code Reasoning via Semantic Equivale…

200 papers

Large Language Models (LLMs) can achieve strong performance on everyday coding tasks, but they can fail on complex tasks that require non-trivial reasoning about program semantics. Finding training examples to teach LLMs to solve these…

Machine Learning · Computer Science 2025-08-29 Antonio Valerio Miceli-Barone , Vaishak Belle , Ali Payani

Recent advances in large language models (LLMs) have improved their performance on coding benchmarks. However, improvement is plateauing due to the exhaustion of readily available high-quality data. Prior work has shown the potential of…

Software Engineering · Computer Science 2026-03-04 Zi Lin , Sheng Shen , Ilia Kulikov , Jingbo Shang , Jason Weston , Yixin Nie

Equational reasoning is one of the key features of pure functional languages such as Haskell. To date, however, such reasoning always took place externally to Haskell, either manually on paper, or mechanised in a theorem prover. This…

Programming Languages · Computer Science 2018-06-12 Niki Vazou , Joachim Breitner , Will Kunkel , David Van Horn , Graham Hutton

Progress in long-context reasoning for large language models (LLMs) has lagged behind other recent advances. This gap arises not only from the intrinsic difficulty of processing long texts, but also from the scarcity of reliable human…

Computation and Language · Computer Science 2026-03-16 Ziyi Yang , Weizhou Shen , Chenliang Li , Ruijun Chen , Fanqi Wan , Ming Yan , Xiaojun Quan , Fei Huang

As large language models (LLMs) become integral to code-related tasks, a central question emerges: Do LLMs truly understand program semantics? We introduce EquiBench, a new benchmark for evaluating LLMs through equivalence checking, i.e.,…

Machine Learning · Computer Science 2025-09-23 Anjiang Wei , Jiannan Cao , Ran Li , Hongyu Chen , Yuhui Zhang , Ziheng Wang , Yuan Liu , Thiago S. F. X. Teixeira , Diyi Yang , Ke Wang , Alex Aiken

Liquid Haskell's refinement-reflection feature augments the Haskell language with theorem proving capabilities, allowing programmers to retrofit their existing code with proofs. But many of these proofs require routine, boilerplate code…

Programming Languages · Computer Science 2017-08-09 Ryan Scott , Vikraman Choudhury , Ryan Newton , Niki Vazou , Ranjit Jhala

Refinement type checkers are a powerful way to reason about functional programs. For example, one can prove properties of a slow, specification implementation, porting the proofs to an optimized implementation that behaves the same. Without…

Programming Languages · Computer Science 2022-07-20 Niki Vazou , Michael Greenberg

Large language models (LLMs) can generate executable code from natural language descriptions, but the resulting programs frequently contain bugs due to hallucinations. In the absence of formal specifications, existing approaches attempt to…

Software Engineering · Computer Science 2026-03-31 Yihan Dai , Sijie Liang , Haotian Xu , Peichu Xie , Sergey Mechtaev

In recent years we have explored using Haskell alongside a traditional mathematical formalism in our large-enrolment university course on topics including logic and formal languages, aiming to offer our students a programming perspective on…

Computers and Society · Computer Science 2022-08-10 Matthew Farrugia-Roberts , Bryn Jeffries , Harald Søndergaard

Synthetic verification techniques such as generating test cases and reward modelling are common ways to enhance the coding capabilities of large language models (LLM) beyond predefined tests. Additionally, code verification has recently…

Artificial Intelligence · Computer Science 2025-07-31 Aleksander Ficek , Somshubra Majumdar , Vahid Noroozi , Boris Ginsburg

Formally verifying properties of software code has been a highly desirable task, especially with the emergence of LLM-generated code. In the same vein, they provide an interesting avenue for the exploration of formal verification and…

Artificial Intelligence · Computer Science 2025-10-02 Balaji Rao , William Eiers , Carlo Lipizzi

Language model-based code completion models have quickly grown in use, helping thousands of developers write code in many different programming languages. However, research on code completion models typically focuses on imperative languages…

Computation and Language · Computer Science 2024-03-25 Tim van Dam , Frank van der Heijden , Philippe de Bekker , Berend Nieuwschepen , Marc Otten , Maliheh Izadi

Obtaining good performance when programming heterogeneous computing platforms poses significant challenges. We present a program transformation environment, implemented in Haskell, where architecture-agnostic scientific C code with semantic…

Programming Languages · Computer Science 2017-01-13 Salvador Tamarit , Julio Mariño , Guillermo Vigueras , Manuel Carro

Autoformalization, the task of automatically translating natural language descriptions into a formal language, poses a significant challenge across various domains, especially in mathematics. Recent advancements in large language models…

Computation and Language · Computer Science 2024-12-09 Zenan Li , Yifan Wu , Zhaoyu Li , Xinming Wei , Xian Zhang , Fan Yang , Xiaoxing Ma

Large language models (LLM), such as Google's Minerva and OpenAI's GPT families, are becoming increasingly capable of solving mathematical quantitative reasoning problems. However, they still make unjustified logical and computational…

Artificial Intelligence · Computer Science 2024-03-28 Jin Peng Zhou , Charles Staats , Wenda Li , Christian Szegedy , Kilian Q. Weinberger , Yuhuai Wu

The research in AI-based formal mathematical reasoning has shown an unstoppable growth trend. These studies have excelled in mathematical competitions like IMO and have made significant progress. This paper focuses on formal verification,…

Artificial Intelligence · Computer Science 2025-06-10 Jialun Cao , Yaojie Lu , Meiziniu Li , Haoyang Ma , Haokun Li , Mengda He , Cheng Wen , Le Sun , Hongyu Zhang , Shengchao Qin , Shing-Chi Cheung , Cong Tian

In this paper, we prove correctness of parallelizing a string matcher using Haskell as a theorem prover. We use refinement types to specify correctness properties, Haskell terms to express proofs and Liquid Haskell to check correctness of…

Programming Languages · Computer Science 2016-10-25 Niki Vazou , Jeff Polakow

SMT-based verifiers have long been an effective means of ensuring safety properties of programs. While these techniques are well understood, we show that they implicitly require eager semantics; directly applying them to a lazy language is…

Programming Languages · Computer Science 2014-01-27 Niki Vazou , Eric L. Seidel , Ranjit Jhala

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

It has been established in recent work that Large Language Models (LLMs) can be prompted to "self-play" conversational games that probe certain capabilities (general instruction following, strategic goal orientation, language understanding…

Computation and Language · Computer Science 2024-06-03 Anne Beyer , Kranti Chalamalasetti , Sherzod Hakimov , Brielen Madureira , Philipp Sadler , David Schlangen
‹ Prev 1 2 3 10 Next ›