相关论文: How Can I Do That with ACL2? Recent Enhancements t…

Verification of algorithms and data structures utilized in modern autonomous and semi-autonomous vehicles for land, sea, air, and space presents a significant challenge. Autonomy algorithms, e.g., route planning, pattern matching, and…

Communication fabrics play a key role in the correctness and performance of modern multi-core processors and systems-on-chip. To enable formal verification, a recent trend is to use high-level micro-architectural models to capture…

This volume contains the proceedings of the Fifteenth International Workshop on the ACL2 Theorem Prover and Its Applications (ACL2-2018), a two-day workshop held in Austin, Texas, USA, on November 5-6, 2018, immediately after FMCAD'18. The…

Calibration strengthens the trustworthiness of black-box models by producing better accurate confidence estimates on given examples. However, little is known about if model explanations can help confidence calibration. Intuitively, humans…

ML models are increasingly deployed in settings with real world interactions such as vehicles, but unfortunately, these models can fail in systematic ways. To prevent errors, ML engineering teams monitor and continuously improve these…

Webextensions can improve web browser privacy, security, and user experience. The APIs offered by the browser to webextensions affect possible functionality. Currently, Chrome transitions to a modified set of APIs called Manifest v3. This…

We describe defret-mutual-generate, a utility for proving ACL2 theorems about large mutually recursive cliques of functions. This builds on previous tools such as defret-mutual and make-flag, which automate parts of the process but still…

To overcome the limitations of both approaches classical and formal for the development of complex software, we proposed a hybrid approach combining the formal approach (Event-B) and the classical approach (UML/OCL). Upstream phases of our…

Reproducibility remains a challenge in machine learning research. While code and data availability requirements have become increasingly common, post-publication verification in journals is still limited and unformalized. This position…

Resources for simulation-based evaluation of conversational recommender systems (CRSs) are scarce. The UserSimCRS toolkit was introduced to address this gap. In this work, we present UserSimCRS v2, a significant upgrade aligning the toolkit…

Googles A2A protocol provides a secure communication framework for AI agents but demonstrates critical limitations when handling highly sensitive information such as payment credentials and identity documents. These gaps increase the risk…

We report our experience formally modelling and verifying CXL.cache, the inter-device cache coherence protocol of the Compute Express Link standard. We have used the Isabelle proof assistant to create a formal model for CXL.cache based on…

While significant progress has been made in automating various aspects of software development through coding agents, there is still significant room for improvement in their bug fixing capabilities. Debugging and investigation of runtime…

Large language models (LLMs) have demonstrated remarkable capabilities in tool learning. In real-world scenarios, user queries are often ambiguous and incomplete, requiring effective clarification. However, existing interactive…

Many collaborative recommender systems leverage social correlation theories to improve suggestion performance. However, they focus on explicit relations between users and they leave out other types of information that can contribute to…

The sequential nature of modern LLMs makes them expensive and slow, and speculative sampling has proven to be an effective solution to this problem. Methods like EAGLE perform autoregression at the feature level, reusing top-layer features…

Text documents, including programs, typically have human-readable semantic structure. Historically, programmatic access to these semantics has required explicit in-document tagging. Especially in systems where the text has an execution…

Recent advances in large language models (LLMs) have enabled natural language interfaces that translate user questions into database queries, such as Text2SQL, Text2SPARQL, and Text2Cypher. While these interfaces enhance database…

This paper introduces ESBMC v7.3, the latest Efficient SMT-Based Context-Bounded Model Checker version, which now incorporates a new clang-based C++ front-end. While the previous CPROVER-based front-end served well for handling C++03…

Explanations have gained an increasing level of interest in the AI and Machine Learning (ML) communities in order to improve model transparency and allow users to form a mental model of a trained ML model. However, explanations can go…