Related papers: CCR 2.0: High-level Reasoning for Conditional Refi…
Contextual refinement (CR) is one of the standard notions of specifying open programs. CR has two main advantages: (i) (horizontal and vertical) compositionality that allows us to decompose a large contextual refinement into many smaller…
Refinement transforms an abstract system model into a concrete, executable program, such that properties established for the abstract model carry over to the concrete implementation. Refinement has been used successfully in the development…
Large language models struggle to catch errors in their own outputs when the review happens in the same session that produced them. This paper introduces Cross-Context Review (CCR), a straightforward method where the review is conducted in…
Contextual refinement and separation logics are successful verification techniques that are very different in nature. First, the former guarantees behavioral refinement between a concrete program and an abstract program while the latter…
Background: Modern Code Review (MCR) is a key component for delivering high-quality software and sharing knowledge among developers. Effective reviews require an in-depth understanding of the code and demand from the reviewers to…
Causal reasoning and compositional reasoning are two core aspirations in AI. Measuring the extent of these behaviors requires principled evaluation methods. We explore a unified perspective that considers both behaviors simultaneously,…
Retrieval-augmented generation (RAG) improves knowledge-intensive question answering by incorporating external evidence. However, existing RAG methods still suffer from hallucinations and subtle reasoning errors. Recent studies introduce…
Causal reasoning and logical reasoning are two important types of reasoning abilities for human intelligence. However, their relationship has not been extensively explored under machine intelligence context. In this paper, we explore how…
Relational program verification is a variant of program verification where one can reason about two programs and as a special case about two executions of a single program on different inputs. Relational program verification can be used for…
This paper introduces a uniform substitution calculus for differential refinement logic dRL. The logic dRL extends the differential dynamic logic dL such that one can simultaneously reason about properties of and relations between hybrid…
Compiler correctness proofs for higher-order concurrent languages are difficult: they involve establishing a termination-preserving refinement between a concurrent high-level source language and an implementation that uses low-level shared…
Conversational recommender systems (CRS) aim to recommend suitable items to users through natural language conversations. For developing effective CRSs, a major technical issue is how to accurately infer user preference from very limited…
Often, when analyzing the behaviour of systems modelled as context-free languages, we wish to know if two languages overlap. To this end, we present an effective semi-decision procedure for regular separability of context-free languages,…
This thesis introduces the "method of structural refinement", which serves as a means of transforming the relational semantics of a modal and/or constructive logic into an 'economical' proof system by connecting two proof-theoretic…
Large language models (LLMs) achieve strong performance by generating long chains of thought, but longer traces always introduce redundant or ineffective reasoning steps. One typical behavior is that they often perform unnecessary…
In this paper, we develop a novel verification technique to reason about programs featuring concurrency, pointers and randomization. While the integration of concurrency and pointers is well studied, little is known about the combination of…
Rewriting logic is naturally concurrent: several subterms of the state term can be rewritten simultaneously. But state terms are global, which makes compositionality difficult to achieve. Compositionality here means being able to decompose…
Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice questions (MCQs). However, standard outcome-based reinforcement learning (RL) on MCQs is risky. While it may improve accuracy, we observe it…
We propose Confidence-guided Refinement Reasoning (C2R), a novel training-free framework applicable to question-answering (QA) tasks across text, image, and video domains. C2R strategically constructs and refines sub-questions and their…
Integrating causal inference (CI) with reinforcement learning (RL) has emerged as a powerful paradigm to address critical limitations in classical RL, including low explainability, lack of robustness and generalization failures. Traditional…