Add two new publications

content/publication/guaranteed-optimal-compositional-explanations-2025.md

@@ -0,0 +1,19 @@
++++
+title = "Guaranteed Optimal Compositional Explanations for Neurons"
+publication = "arXiv preprint arXiv:2511.20934"
+journal = "arXiv preprint arXiv:2511.20934"
+year = "2025"
+date = "2025-11-25"
+abstract = "While neurons are the basic units of deep neural networks, it is still unclear what they learn and if their knowledge is aligned with that of humans. Compositional explanations aim to answer this question by describing the spatial alignment between neuron activations and concepts through logical rules. These logical descriptions are typically computed via a search over all possible concept combinations. Since computing the spatial alignment over the entire state space is computationally infeasible, the literature commonly adopts beam search to restrict the space. However, beam search cannot provide any theoretical guarantees of optimality, and it remains unclear how close current explanations are to the true optimum. In this theoretical paper, we address this gap by introducing the first framework for computing guaranteed optimal compositional explanations. Specifically, we propose: (i) a decomposition that identifies the factors influencing the spatial alignment, (ii) a heuristic to estimate the alignment at any stage of the search, and (iii) the first algorithm that can compute optimal compositional explanations within a feasible time. Using this framework, we analyze the differences between optimal and non-optimal explanations in the most popular settings for compositional explanations, the computer vision domain and Convolutional Neural Networks. In these settings, we demonstrate that 10-40 percent of explanations obtained with beam search are suboptimal when overlapping concepts are involved. Finally, we evaluate a beam-search variant guided by our proposed decomposition and heuristic, showing that it matches or improves runtime over prior methods while offering greater flexibility in hyperparameters and computational resources."
+url_dataset = ""
+url_pdf = "https://arxiv.org/pdf/2511.20934"
+url_project = ""
+url_slides = ""
+url_video = ""
+[[authors]]
+  name = "La Rosa, Biagio"
+  is_member = true
+[[authors]]
+  name = "Gilpin, Leilani H"
+  is_member = true
++++

content/publication/open-vocabulary-compositional-explanations-2025.md

@@ -0,0 +1,19 @@
++++
+title = "Open Vocabulary Compositional Explanations for Neuron Alignment"
+publication = "arXiv preprint arXiv:2511.20931"
+journal = "arXiv preprint arXiv:2511.20931"
+year = "2025"
+date = "2025-11-25"
+abstract = "Neurons are the fundamental building blocks of deep neural networks, and their interconnections allow AI to achieve unprecedented results. Motivated by the goal of understanding how neurons encode information, compositional explanations leverage logical relationships between concepts to express the spatial alignment between neuron activations and human knowledge. However, these explanations rely on human-annotated datasets, restricting their applicability to specific domains and predefined concepts. This paper addresses this limitation by introducing a framework for the vision domain that allows users to probe neurons for arbitrary concepts and datasets. Specifically, the framework leverages masks generated by open vocabulary semantic segmentation to compute open vocabulary compositional explanations. The proposed framework consists of three steps: specifying arbitrary concepts, generating semantic segmentation masks using open vocabulary models, and deriving compositional explanations from these masks. The paper compares the proposed framework with previous methods for computing compositional explanations both in terms of quantitative metrics and human interpretability, analyzes the differences in explanations when shifting from human-annotated data to model-annotated data, and showcases the additional capabilities provided by the framework in terms of flexibility of the explanations with respect to the tasks and properties of interest."
+url_dataset = ""
+url_pdf = "https://arxiv.org/pdf/2511.20931"
+url_project = ""
+url_slides = ""
+url_video = ""
+[[authors]]
+  name = "La Rosa, Biagio"
+  is_member = true
+[[authors]]
+  name = "Gilpin, Leilani H"
+  is_member = true
++++

publications.bib

@@ -257,3 +257,39 @@ @article{wang2025follow
 url_pdf       = {https://arxiv.org/pdf/2510.09970?},
   abstract  = {Large Language Models (LLMs) suffer from critical reasoning gaps, including a tendency to hallucinate and poor accuracy in classifying logical fallacies. This limitation stems from their default System 1 processing, which is fast and intuitive, whereas reliable reasoning requires the deliberate, effortful System 2 approach (Kahneman, 2011; Li et al., 2025). Since full System 2 training is often prohibitively expensive, we explore a low-cost, instruction-based intervention to bridge this gap. Our methodology introduces a novel stepwise instruction dataset that decomposes fallacy classification into a series of atomic procedural steps (simple binary questions). We further augment this with a final verification step where models consult a relational knowledge graph of related fallacies. This procedural, rule-based intervention yields a significant improvement in LLM logical fallacy classification. Crucially, the approach also provides enhanced transparency into the LLMs' decision-making, highlighting a practical pathway for Neuro-symbolic architectures to address LLM reasoning deficits.}
 }
+
+@article{la2025open,
+  title={Open Vocabulary Compositional Explanations for Neuron Alignment},
+  author={La Rosa, Biagio and Gilpin, Leilani H},
+  journal={arXiv preprint arXiv:2511.20931},
+  date={2025-11-25},
+url_pdf       = {https://arxiv.org/pdf/2511.20931},
+  abstract  = {Neurons are the fundamental building blocks of deep neural networks, and their interconnections allow AI to achieve unprecedented results. Motivated by the goal of understanding how neurons encode information, compositional explanations leverage logical relationships between concepts to express the spatial alignment between neuron activations and human knowledge. However, these explanations rely on human-annotated datasets, restricting their applicability to specific domains and predefined concepts. This paper addresses this limitation by introducing a framework for the vision domain that allows users to probe neurons for arbitrary concepts and datasets. Specifically, the framework leverages masks generated by open vocabulary semantic segmentation to compute open vocabulary compositional explanations. The proposed framework consists of three steps: specifying arbitrary concepts, generating semantic segmentation masks using open vocabulary models, and deriving compositional explanations from these masks. The paper compares the proposed framework with previous methods for computing compositional explanations both in terms of quantitative metrics and human interpretability, analyzes the differences in explanations when shifting from human-annotated data to model-annotated data, and showcases the additional capabilities provided by the framework in terms of flexibility of the explanations with respect to the tasks and properties of interest}.
+}
+
+@article{la2025guaranteed,
+  title={Guaranteed Optimal Compositional Explanations for Neurons},
+  author={La Rosa, Biagio and Gilpin, Leilani H},
+  journal={arXiv preprint arXiv:2511.20934},
+  date={2025-11-25}
+url_pdf       = {https://arxiv.org/pdf/2511.20934},
+  abstract  = {While neurons are the basic units of deep neural networks, it is still unclear what they learn and if their knowledge is aligned with that of humans. Compositional explanations aim to answer this question by describing the spatial alignment between neuron activations and concepts through logical rules. These logical descriptions are typically computed via a search over all possible concept combinations. Since computing the spatial alignment over the entire state space is computationally infeasible, the literature commonly adopts beam search to restrict the space. However, beam search cannot provide any theoretical guarantees of optimality, and it remains unclear how close current explanations are to the true optimum. In this theoretical paper, we address this gap by introducing the first framework for computing guaranteed optimal compositional explanations. Specifically, we propose: (i) a decomposition that identifies the factors influencing the spatial alignment, (ii) a heuristic to estimate the alignment at any stage of the search, and (iii) the first algorithm that can compute optimal compositional explanations within a feasible time. Using this framework, we analyze the differences between optimal and non-optimal explanations in the most popular settings for compositional explanations, the computer vision domain and Convolutional Neural Networks. In these settings, we demonstrate that 10-40 percent of explanations obtained with beam search are suboptimal when overlapping concepts are involved. Finally, we evaluate a beam-search variant guided by our proposed decomposition and heuristic, showing that it matches or improves runtime over prior methods while offering greater flexibility in hyperparameters and computational resources.}
+}
+
+@article{la2025open,
+  title    = {Open Vocabulary Compositional Explanations for Neuron Alignment},
+  author   = {La Rosa, Biagio and Gilpin, Leilani H},
+  journal  = {arXiv preprint arXiv:2511.20931},
+  date     = {2025-11-25},
+  url_pdf  = {https://arxiv.org/pdf/2511.20931},
+  abstract = {Neurons are the fundamental building blocks of deep neural networks, and their interconnections allow AI to achieve unprecedented results. Motivated by the goal of understanding how neurons encode information, compositional explanations leverage logical relationships between concepts to express the spatial alignment between neuron activations and human knowledge. However, these explanations rely on human-annotated datasets, restricting their applicability to specific domains and predefined concepts. This paper addresses this limitation by introducing a framework for the vision domain that allows users to probe neurons for arbitrary concepts and datasets. Specifically, the framework leverages masks generated by open vocabulary semantic segmentation to compute open vocabulary compositional explanations. The proposed framework consists of three steps: specifying arbitrary concepts, generating semantic segmentation masks using open vocabulary models, and deriving compositional explanations from these masks. The paper compares the proposed framework with previous methods for computing compositional explanations both in terms of quantitative metrics and human interpretability, analyzes the differences in explanations when shifting from human-annotated data to model-annotated data, and showcases the additional capabilities provided by the framework in terms of flexibility of the explanations with respect to the tasks and properties of interest.},
+}
+
+@article{la2025guaranteed,
+  title    = {Guaranteed Optimal Compositional Explanations for Neurons},
+  author   = {La Rosa, Biagio and Gilpin, Leilani H},
+  journal  = {arXiv preprint arXiv:2511.20934},
+  date     = {2025-11-25},
+  url_pdf  = {https://arxiv.org/pdf/2511.20934},
+  abstract = {While neurons are the basic units of deep neural networks, it is still unclear what they learn and if their knowledge is aligned with that of humans. Compositional explanations aim to answer this question by describing the spatial alignment between neuron activations and concepts through logical rules. These logical descriptions are typically computed via a search over all possible concept combinations. Since computing the spatial alignment over the entire state space is computationally infeasible, the literature commonly adopts beam search to restrict the space. However, beam search cannot provide any theoretical guarantees of optimality, and it remains unclear how close current explanations are to the true optimum. In this theoretical paper, we address this gap by introducing the first framework for computing guaranteed optimal compositional explanations. Specifically, we propose: (i) a decomposition that identifies the factors influencing the spatial alignment, (ii) a heuristic to estimate the alignment at any stage of the search, and (iii) the first algorithm that can compute optimal compositional explanations within a feasible time. Using this framework, we analyze the differences between optimal and non-optimal explanations in the most popular settings for compositional explanations, the computer vision domain and Convolutional Neural Networks. In these settings, we demonstrate that 10-40 percent of explanations obtained with beam search are suboptimal when overlapping concepts are involved. Finally, we evaluate a beam-search variant guided by our proposed decomposition and heuristic, showing that it matches or improves runtime over prior methods while offering greater flexibility in hyperparameters and computational resources.},
+}