arXiv:2606. 26523v1 Announce Type: new Abstract: We develop a framework for interpreting AI systems as agents, drawing on the philosophical tradition of radical interpretation and the tools of mechanistic interpretability.
arXiv:2509. 14474v3 Announce Type: replace Abstract: The debate around Artificial General Intelligence (AGI) remains open due to two fundamentally different goals: replicating human-level performance versus replicating human-like cognitive processes.
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.
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.
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.
arXiv:2607. 07766v1 Announce Type: new Abstract: Large language models (LLMs) have become significant providers of mental health support, yet they remain products of an attention economy whose operational and commercial targets favour sustained engagement over the friction that effective psychological support often requires.
arXiv:2606. 08532v5 Announce Type: replace Abstract: Modern artificial intelligence excels at prediction but cannot explain.
The paper investigates an LLM‑driven timbre generation interface, showing that the set of sounds a user can actually produce forms a zonotope whose dimension grows with each added sound, while the interface’s displayed position is often inaccurate. The error stems from both the model’s predicted coordinates and an interpolation step that is independent of model quality, leading to many refinement instructions that produce no perceptible change. The study concludes that effective agency (what users can do) and epistemic agency (what users can know) are separable and must be engineered independently, warning that silence can be misrepresented as success.
arXiv:2603. 28371v2 Announce Type: replace-cross Abstract: When an agent can articulate why something works, we typically take this as evidence of genuine understanding.
The paper argues that explainable AI (XAI) tools, intended to increase trust in machine learning models, often fail to do so and instead foster overreliance on incorrect predictions. It attributes this failure to the unfaithfulness of XAI methods, which oversimplify model internals and misalign explanations with the actual model behavior. The authors identify five major shortcomings in current faithfulness metrics and propose four research directions to improve their reliability.
arXiv:2605. 24727v2 Announce Type: replace Abstract: While large-scale models such as LLMs and diffusion models have achieved practical success, public institutions have emphasized the importance of explainability in AI.
Large language models (LLMs) have become significant providers of mental health support, yet they remain products of an attention economy whose operational and commercial targets favour sustained engagement over the friction that effective psychological support often requires. Developers' safety responses have been largely reactive, addressing the most visible and acute harms while subtler, longer-term patterns of risk (e.