arXiv AI By Hector Zenil, Abicumaran Uthamacumaran, Luan Ozelim

Large Language Models As Shannon Lossy Compressors Not Solomonoff Induction Estimators: The Singularity Is Not Near Without Symbolic Model Synthesis

Read the original on arXiv AI →

The paper argues that Large Language Models (LLMs) do not function as Solomonoff induction estimators because their training objectives—cross‑entropy, negative log‑likelihood, and next‑token prediction—optimize fit to a supplied conditional distribution rather than a program‑weighted universal mixture. It further contends that additional computation alone does not transform these models into optimal predictors without external hyper‑parameter or architectural changes. The authors suggest that neurosymbolic machine learning, exemplified by models such as Fable and Astra, represents a shift toward symbolic model synthesis, moving beyond purely statistical LLMs.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI
Aug 12

On Solomonoff Induction in Large Language Models and the Limits of Self-Improving: The Singularity Is Not Near Without Symbolic Model Synthesis

arXiv:2601. 05280v3 Announce Type: replace-cross Abstract: On the one hand, the question of whether large language models (LLMs) are Solomonoff induction estimators has become an explicit question at the intersection of Algorithmic Information Theory (AIT) and Machine Learning (ML) of great interest.

By Hector Zenil
arXiv Machine Learning
Oct 22

Approximate Solomonoff Induction: On the Robustness of Learned Universal Predictors

The paper investigates how well practical machine‑learning algorithms approximate Solomonoff’s universal predictor when trained by minimizing log‑loss over diverse datasets. It establishes tight bounds on the worst‑case increase in prediction error caused by approximating the Bayesian mixture predictor, showing that while the excess error can be large in low‑prior environments, it remains bounded on average and under distribution shifts. The authors also extend their analysis to finite‑sample settings relevant to neural networks and Transformers.

By Qian Li, Shang-Hua Teng
arXiv AI
Oct 9

Language Modeling is Monotone Compression

The paper investigates the relationship between large language models (LLMs) and compression, showing that LLMs, modeled as next‑token predictors, are equivalent to monotone (order‑preserving) compression algorithms with an error gap of at most 2. It further proves that this monotonicity is necessary for the equivalence only if cryptographic one‑way functions exist, and derives a cryptographic corollary linking next‑bit pseudoentropy to monotone incompressibility.

By Noam Mazor, Andrew Morgan, Rafael Pass