Paper Detail
Enrico Vompa, Tanel Tammet
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{vompa2026scaling,
title = {The Scaling Properties of Implicit Deductive Reasoning in Transformers},
author = {Enrico Vompa and Tanel Tammet},
year = {2026},
abstract = {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.},
url = {https://huggingface.co/papers/2605.04330},
keywords = {Horn clauses, Transformers, implicit deductive reasoning, chain-of-thought, bidirectional prefix mask, algorithmic alignment, depth-bounded Transformers, huggingface daily},
eprint = {2605.04330},
archiveprefix = {arXiv},
}
{}