Representational convergence across 16 LLMs on 800 reasoning problems is stronger for failed tasks and pre-decision stages but shows minimal causal influence on predictions, pointing to shared processing constraints over shared reasoning.
Correcting
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Decoding alignment metrics can remain high and unchanged even when encoding manifold topology is causally altered, so they do not imply similar function or computation across neural populations.
citing papers explorer
-
Convergence Without Understanding: When Language Models Agree on Representations but Disagree on Reasoning
Representational convergence across 16 LLMs on 800 reasoning problems is stronger for failed tasks and pre-decision stages but shows minimal causal influence on predictions, pointing to shared processing constraints over shared reasoning.
-
Decoding Alignment without Encoding Alignment: A critique of similarity analysis in neuroscience
Decoding alignment metrics can remain high and unchanged even when encoding manifold topology is causally altered, so they do not imply similar function or computation across neural populations.