ENIGMA: The Geometry of Reasoning and Alignment in Large-Language Models

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Seneque, Gareth, Ho, Lap-Hang, Saeedi, Nafise Erfanian, Molendijk, Jeffrey, Kuperman, Ariel, Elson, Tim
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915556583538688
author Seneque, Gareth
Ho, Lap-Hang
Saeedi, Nafise Erfanian
Molendijk, Jeffrey
Kuperman, Ariel
Elson, Tim
author_facet Seneque, Gareth
Ho, Lap-Hang
Saeedi, Nafise Erfanian
Molendijk, Jeffrey
Kuperman, Ariel
Elson, Tim
contents We present Entropic Mutual-Information Geometry Large-Language Model Alignment (ENIGMA), a novel approach to Large-Language Model (LLM) training that jointly improves reasoning, alignment and robustness by treating an organisation's policies/principles as directions to move on a model's information manifold. Our single-loop trainer combines Group-Relative Policy Optimisation (GRPO), an on-policy, critic-free RL method with Chain-of-Thought (CoT)-format only rewards; a Self-Supervised Alignment with Mutual Information (SAMI)-style symmetric InfoNCE auxiliary; and an entropic Sinkhorn optimal-transport regulariser on hidden-state distributions to bound geometry drift. We also introduce infoNCE metrics that specialise to a standard MI lower bound under matched negatives to measure how strongly a model's CoT encodes these policies. These metrics include a Sufficiency Index (SI) that enables the selection and creation of principles that maximise downstream performance prior to training. In our experiments using small (1B) LLMs, high-SI principles predict steadier training dynamics and improved benchmark performance over GRPO ablations. Our information-geometry analysis of trained models validates desirable structural change in the manifold. These results support our hypothesis that reasoning, alignment, and robustness are projections of a single information-geometric objective, and that models trained using ENIGMA demonstrate principled reasoning without the use of a reward model, offering a path to trusted capability
format Preprint
id arxiv_https___arxiv_org_abs_2510_11278
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ENIGMA: The Geometry of Reasoning and Alignment in Large-Language Models
Seneque, Gareth
Ho, Lap-Hang
Saeedi, Nafise Erfanian
Molendijk, Jeffrey
Kuperman, Ariel
Elson, Tim
Machine Learning
Artificial Intelligence
Computation and Language
68T50
I.2.7
We present Entropic Mutual-Information Geometry Large-Language Model Alignment (ENIGMA), a novel approach to Large-Language Model (LLM) training that jointly improves reasoning, alignment and robustness by treating an organisation's policies/principles as directions to move on a model's information manifold. Our single-loop trainer combines Group-Relative Policy Optimisation (GRPO), an on-policy, critic-free RL method with Chain-of-Thought (CoT)-format only rewards; a Self-Supervised Alignment with Mutual Information (SAMI)-style symmetric InfoNCE auxiliary; and an entropic Sinkhorn optimal-transport regulariser on hidden-state distributions to bound geometry drift. We also introduce infoNCE metrics that specialise to a standard MI lower bound under matched negatives to measure how strongly a model's CoT encodes these policies. These metrics include a Sufficiency Index (SI) that enables the selection and creation of principles that maximise downstream performance prior to training. In our experiments using small (1B) LLMs, high-SI principles predict steadier training dynamics and improved benchmark performance over GRPO ablations. Our information-geometry analysis of trained models validates desirable structural change in the manifold. These results support our hypothesis that reasoning, alignment, and robustness are projections of a single information-geometric objective, and that models trained using ENIGMA demonstrate principled reasoning without the use of a reward model, offering a path to trusted capability
title ENIGMA: The Geometry of Reasoning and Alignment in Large-Language Models
topic Machine Learning
Artificial Intelligence
Computation and Language
68T50
I.2.7
url https://arxiv.org/abs/2510.11278