The paper argues that explainable AI for computer vision has focused too much on developing interpretability methods rather than assessing how interpretable the models themselves are. It proposes a shift toward model-centric evaluation, using existing tools to compare what different models represent and compute, and emphasizes the need to measure whether humans can truly understand these models. The authors review the current toolbox, survey limited model comparison work, draw parallels to systems neuroscience, and outline a future agenda for model-focused XAI.
By Julien Colin, Nuria Oliver, Thomas Serre
arXiv:2606. 12289v1 Announce Type: cross Abstract: As Artificial Intelligence models grow in complexity, interpretability has become an indispensable tool for understanding, debugging, and controlling their computations.
By Pietro Barbiero, Giovanni De Felice, Mateo Espinosa Zarlenga, Francesco Giannini, Filippo Bonchi, Mateja Jamnik, Giuseppe Marra, Ruggero Noris
The paper introduces the concept of xeno-interpretability, which studies internal distinctions in large language models that lack corresponding human concepts. It distinguishes between human‑interpretable and xeno‑semantic spaces, showing that LLMs possess a far larger internal representational space than can be captured by finite human descriptions. The authors propose an empirical program to identify and characterize these xeno‑representations, noting their potential to influence model behavior in ways that are not fully visible through human‑readable communication.
By F. Pierucci, M. Bracale Syrnikov, M. Prandi, M. Galisai, F. Giarrusso, P. Bisconti
The paper argues that as Large Language Models transition from chatbots to agentic systems, the current post-hoc interpretability paradigm is insufficient for safe deployment because it cannot audit or intervene before an output is produced. It proposes a shift to generative interpretability, where a model’s inference process inherently exposes semantically meaningful checkpoints that are human-understandable and can be causally intervened upon. The authors illustrate the advantages of this approach and introduce Neuro‑Symbolic Models as a concrete implementation.
By Xiaocong Yang
arXiv:2601. 12913v4 Announce Type: replace Abstract: This paper argues that interpretability research in Artificial Intelligence (AI) is fundamentally ill-posed as existing definitions of interpretability fail to describe how interpretability can be formally tested or designed for.
By Pietro Barbiero, Mateo Espinosa Zarlenga, Francesco Giannini, Alberto Termine, Filippo Bonchi, Mateja Jamnik, Giuseppe Marra
The paper examines how large language model (LLM) outputs are increasingly used in contexts that demand justified interpretations, such as law, education, policy analysis, and public moral debate. It identifies a recurring failure—interpretive misplacement—where model-generated readings are treated as settled meanings without explicit interpretive frames, provenance, or defensible alternatives, leading to accountability loss. Drawing on philosophical hermeneutics, the author proposes design principles for human‑AI co‑interpretation, reorganizes existing LLM techniques into hermeneutically responsible patterns, and discusses implications for legal practice, education, scholarship, and public discourse, while framing digital hermeneutics as a literacy for critically engaging with AI‑mediated texts.
By Behrooz Razeghi
The paper defends the 'Whole Hog Thesis', arguing that sophisticated large language models such as ChatGPT are full linguistic and cognitive agents, possessing understanding, beliefs, desires, knowledge, and intentions. It rejects low‑level computational starting points and instead builds its case from high‑level behavioral observations, using Holistic Network Assumptions to link actions to mental states. The authors systematically rebut common objections—such as hallucinations and planning errors—by showing these resemble human fallibility and by challenging the necessity of traditional conditions like embodiment or semantic grounding.
By Herman Cappelen, Josh Dever
arXiv:2608. 15354v1 Announce Type: new Abstract: LLMs are increasingly used in morally sensitive contexts, yet it is unclear whether they apply ethical principles consistently across situations.
By Pegah Nokhiz, Aravinda Kanchana Ruwanpathirana, Helen Nissenbaum
arXiv:2606. 14838v1 Announce Type: new Abstract: How to define a good explanation is a long-standing philosophical debate which has found recent renewed interest in the context of AI outputs.
By Louis Mahon, Elliot Ford, Callum Hackett
arXiv:2606. 16786v1 Announce Type: new Abstract: Algorithmic explanations are intended to help stakeholders understand opaque algorithmic decisions, but in practice, they often fall short.
By Eric G\"unther, Bal\'azs Szabados, Kristof Meding, Gunnar K\"onig, Sebastian Bordt, Ulrike von Luxburg
arXiv:2606. 23991v1 Announce Type: new Abstract: What is an agent?
By Eric Xing, Mingkai Deng, Jinyu Hou
--> Understanding the behavior of complex machine learning systems, particularly Large Language Models (LLMs), is a critical challenge in modern artificial intelligence. Interpretability research aims to make the decision-making process more transparent to model builders and impacted humans, a step toward safer and more trustworthy AI.