Related papers: A Tool for Automated Reasoning About Traces Based …
Intelligent coding systems are transforming software development by enabling users to specify code behavior in natural language. However, the opaque decision-making of AI-driven coders raises trust and usability concerns, particularly for…
Explaining with examples is an intuitive way to justify AI decisions. However, it is challenging to understand how a decision value should change relative to the examples with many features differing by large amounts. We draw from real…
The existence of trace links between artifacts of the software development life cycle can improve the efficiency of many activities during software development, maintenance and operations. Unfortunately, the creation and maintenance of…
In most safety-critical domains the need for traceability is prescribed by certifying bodies. Trace links are generally created among requirements, design, source code, test cases and other artifacts, however, creating such links manually…
We propose a novel dependency-based hybrid tree model for semantic parsing, which converts natural language utterance into machine interpretable meaning representations. Unlike previous state-of-the-art models, the semantic information is…
Machine learning models make mistakes, yet sometimes it is difficult to identify the systematic problems behind the mistakes. Practitioners engage in various activities, including error analysis, testing, auditing, and red-teaming, to form…
Safety-critical system's failure or malfunction can cause loss of human lives or damage to the physical environment; therefore, continuous safety assessment is crucial for such systems. In many domains this includes the use of Safety…
Selective rationalization aims to produce decisions along with rationales (e.g., text highlights or word alignments between two sentences). Commonly, rationales are modeled as stochastic binary masks, requiring sampling-based gradient…
We present Turnstile+, a high-level, macros-based metaDSL for building dependently typed languages. With it, programmers may rapidly prototype and iterate on the design of new dependently typed features and extensions. Or they may create…
The goal of data attribution is to trace model predictions back to training data. Despite a long line of work towards this goal, existing approaches to data attribution tend to force users to choose between computational tractability and…
In conversational recommender systems (CRSs), conversations usually involve a set of items and item-related entities or attributes, e.g., director is a related entity of a movie. These items and item-related entities are often mentioned…
Vehicles in public traffic that are equipped with Automated Driving Systems are subject to a number of expectations: Among other aspects, their behavior should be safe, conforming to the rules of the road and provide mobility to their…
Terminological knowledge representation systems (TKRSs) are tools for designing and using knowledge bases that make use of terminological languages (or concept languages). We analyze from a theoretical point of view a TKRS whose…
Explicit reasoning models are trained to produce intermediate reasoning traces before final answers, but downstream fine-tuning is often performed on ordinary instruction-response data that contains no such traces. We show that this…
Since Knowledge Graphs are often incomplete, link prediction methods are adopted for predicting missing facts. Scalable embedding based solutions are mostly adopted for this purpose, however, they lack comprehensibility, which may be…
Modern research heavily relies on software. A significant challenge researchers face is understanding the complex software used in specific research fields. We target two scenarios in this context, namely long onboarding times for newcomers…
Logical specifications play a key role in the formal analysis of behavioural models. Automating the derivation of such specifications is particularly valuable in complex systems, where manual construction is time-consuming and error-prone.…
Semantic parsing aims to map natural language utterances onto machine interpretable meaning representations, aka programs whose execution against a real-world environment produces a denotation. Weakly-supervised semantic parsers are trained…
The Tarskian classical relevant logic TR arises from Tarski's work on the foundations of the calculus of relations and on first-order logic restricted to finitely many variables, presented by Tarski and Givant their book, A Formalization of…
Starting with a collection of traces generated by process executions, process discovery is the task of constructing a simple model that describes the process, where simplicity is often measured in terms of model size. The challenge of…