arXiv subjects

Mark Dras

Publications and source records attributed to Mark Dras.

3 recordsLinked to original sources

arXiv2026

Process-Constituted Intelligence: A Shared Criterion for Humans and Machines

Intelligence is constituted by \textit{process} (iterative activity through which output emerges), not in the output itself. Generative AI (GenAI) is trained on \textit{traces} (textual and visual residues of human cognitive processes), reproducing samples from a distribution of those traces. Its outputs resemble reasoning, problem-solving, and creativity, yet the activity that produces such outputs in humans remains largely absent. Current GenAI is, therefore, weakly equivalent to the cognition it imitates, matching outputs while process stays absent or opaque. The cognitive sciences have long distinguished between weak and strong equivalence. Here, we define \textit{strong} equivalence across seven process features, assessable against human and machine cognition. Our process-based account addresses a symmetric risk: GenAI tools that outsource a person's generative processes may leave critical capacities unbuilt. We specify design principles for GenAI that instantiate more process and preserve rather than erode human judgment and creativity, and outline process audits that make strong equivalence testable.

cs.AI↗

arXiv2026

Beyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering Robustness

How do the methods used to train language models to refuse harmful requests shape how that refusal actually works inside the model? We compare three post-training methods - supervised fine-tuning, reasoning-augmented fine-tuning (training on reasoning chains that justify a safety decision), and preference optimization (ORPO) - across three architecturally distinct models (Llama-3.1-8B, Gemma-2-9B, Qwen3-8B). We find that training method, not just data, reshapes how refusal is computed internally: reasoning-augmented training consistently produces a distinct kind of refusal computation, visible across all three models, while architecture independently shapes internal structure and how reliably refusal can be steered. Most importantly, no method we study achieves all three properties we would want from safe alignment at once: refusal that isn't concentrated in a few fragile components, safety gains that don't cost general capability, and safety behavior correctable through small, targeted edits. We caution against treating current post-training methods as a solved, reliable defense, especially for security-critical use. Code and models are available in https://github.com/hoangcuongnguyen2001/Beyond-Shallow-Alignment.

cs.CL↗

arXiv2026

Over-Refusal and Representation Subspaces: A Mechanistic Analysis of Task-Conditioned Refusal in Aligned LLMs

Aligned language models that are trained to refuse harmful requests also exhibit over-refusal: they decline safe instructions that seemingly resemble harmful instructions. A natural approach is to ablate the global refusal direction, steering the hidden-state vectors away or towards the harmful-refusal examples, but this corrects over-refusal only incidentally while disrupting the broader refusal mechanism. In this work, we analyse the representational geometry of both refusal types to understand why this happens. We show that harmful-refusal directions are task-agnostic and can be captured by a single global vector, whereas over-refusal directions are task-dependent: they reside within the benign task-representation clusters, vary across tasks, and span a higher-dimensional subspace. Linear probing suggests that the two refusal types are representationally distinct from the early transformer layers. These findings provide a mechanistic explanation of why global direction ablation alone cannot address over-refusal, and establish that task-specific geometric interventions are necessary.

cs.CL↗