The Scaling Properties of Implicit Deductive Reasoning in Transformers
We investigate the scaling properties of implicit deductive reasoning over Horn clauses in depth-bounded Transformers. By systematically decorrelating provability from spurious features and enforcing algorithmic alignment, we find that in sufficiently deep models with a bidirectional prefix mask, implicit reasoning approaches explicit CoT performance across graph topologies and problem widths, though CoT remains necessary for depth extrapolation.
Record details
Published: 5 May 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Finance, VC & PE
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
arXiv · 6 May 2026
When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models
arXiv · 7 May 2026
RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs
arXiv · 3 May 2026
Activation Differences Reveal Backdoors: A Comparison of SAE Architectures
arXiv · 8 May 2026
Quality-Conditioned Agreement in Automated Short Answer Scoring: Mid-Range Degradation and the Impact of Task-Specific Adaptation
arXiv · 8 May 2026
Beyond Anthropomorphism: Exploring the Roles of Perceived Non-humanity and Structural Similarity in Deep Self-Disclosure Toward Generative AI
arXiv · 13 May 2026
How to cite this record
ethics.ai (5 May 2026), “The Scaling Properties of Implicit Deductive Reasoning in Transformers,” evidence record 4943, https://ethics.ai/record/4943 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.