Related papers: Data-driven Circuit Discovery for Interpretability…

Providing textual concept-based explanations for neurons in deep neural networks (DNNs) is of importance in understanding how a DNN model works. Prior works have associated concepts with neurons based on examples of concepts or a…

Traditional clustering methods often perform clustering with low-level indiscriminative representations and ignore relationships between patterns, resulting in slight achievements in the era of deep learning. To handle this problem, we…

Circuit discovery has gradually become one of the prominent methods for mechanistic interpretability, and research on circuit completeness has also garnered increasing attention. Methods of circuit discovery that do not guarantee…

Most common mechanistic models are traditionally presented in mathematical forms to explain a given physical phenomenon. Machine learning algorithms, on the other hand, provide a mechanism to map the input data to output without explicitly…

Spoken language change detection (LCD) refers to identifying the language transitions in a code-switched utterance. Similarly, identifying the speaker transitions in a multispeaker utterance is known as speaker change detection (SCD). Since…

Language models are trained on large volumes of text, and as a result their parameters might contain a significant body of factual knowledge. Any downstream task performed by these models implicitly builds on these facts, and thus it is…

Engineering design operates through hierarchical abstraction from system specifications to component implementations, requiring visual understanding coupled with mathematical reasoning at each level. While Multi-modal Large Language Models…

Existing query languages for data discovery exhibit system-driven designs that emphasize database features and functionality over user needs. We propose a re-prioritization of the client through an introduction of a language-driven approach…

Large Language Models (LLMs) have demonstrated promising reasoning capabilities in robotics; however, their application in multi-robot systems remains limited, particularly in handling task dependencies. This paper introduces DART-LLM, a…

Neural Language Models of Code, or Neural Code Models (NCMs), are rapidly progressing from research prototypes to commercial developer tools. As such, understanding the capabilities and limitations of such models is becoming critical.…

As large language models (LLMs) advance toward expert-level performance in engineering domains, reliable reasoning under user-specified constraints becomes critical. In circuit analysis, for example, a numerically correct solution is…

Regardless of its foundational role in human discovery and sense-making, abductive reasoning--the inference of the most plausible explanation for an observation--has been relatively underexplored in Large Language Models (LLMs). Despite the…

Mechanistic interpretability work attempts to reverse engineer the learned algorithms present inside neural networks. One focus of this work has been to discover 'circuits' -- subgraphs of the full model that explain behaviour on specific…

Large Language Models (LLMs), despite their remarkable capabilities, are hampered by hallucinations. A particularly challenging variant, knowledge overshadowing, occurs when one piece of activated knowledge inadvertently masks another…

Recent work has shown that computation in language models may be human-understandable, with successful efforts to localize and intervene on both single-unit features and input-output circuits. Here, we introduce an approach which extends…

Statistical model discovery is a challenging search over a vast space of models subject to domain-specific constraints. Efficiently searching over this space requires expertise in modeling and the problem domain. Motivated by the domain…

We investigate the processing of idiomatic expressions in transformer-based language models using a novel set of techniques for circuit discovery and analysis. First discovering circuits via a modified path patching algorithm, we find that…

Learning causal structure from observational data is central to scientific modeling and decision-making. Constraint-based methods aim to recover conditional independence (CI) relations in a causal directed acyclic graph (DAG). Classical…

Multimodal deception detection aims to identify deceptive behavior by analyzing audiovisual cues for forensics and security. In these high-stakes settings, investigators need verifiable evidence connecting audiovisual cues to final…

How to generate a large, realistic set of tables along with joinability relationships, to stress-test dataset discovery methods? Dataset discovery methods aim to automatically identify related data assets in a data lake. The development and…