LANTERN: Illuminating Hidden Mathematical Knowledge in Language Models

arXiv:2609.32264 · cs.CL · Submitted 2026-09-26 · Read on arXiv

cs.CL

Submitted: 2026-09-26

Updated: 2026-09-26

Terminology

• Core — 11× in this paper · explained in 2 episodes
• Verification — 10× in this paper · explained in 2 episodes
• AUC — 7× in this paper · explained in 2 episodes
• Embeddings — 7× in this paper · explained in 2 episodes
• Knowledge Graph — 4× in this paper · explained in 7 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Knowledge graphs — 3× in this paper · explained in 2 episodes
• On-Line Encyclopedia of Integer Sequences — 3× in this paper
• Adam — 2× in this paper · explained in 2 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Axioms — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Homogenization — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Provenance — 1× in this paper · explained in 4 episodes
• Quantum Physics — 1× in this paper · explained in 10 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Symbolic Regression — 1× in this paper · explained in 5 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• OEIS Open: How many conjectures can language models turn into theorems?
• FACT: Learning Governing Abstractions Behind Integer Sequences
• Discovering Latent Knowledge in Language Models Without Supervision
• Can LLM generate interesting mathematical research problems?
• Mapping Mathematical Hardness: Machine-Assisted Conjecture Discovery and the Quantification of Non-Triviality
• Deep Symbolic Regression for Recurrent Sequences
• STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving
• Discovering emergent connections in quantum physics research via dynamic word embeddings
• Mathematical exploration and discovery at scale
• Accelerating scientific discovery with Co-Scientist
• Generating Interesting Scientific Ideas using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaders
• A Triumvirate of AI Driven Theoretical Discovery
• On the Cryptomorphism between Davis' Subset Lattices, Atomic Lattices, and Closure Systems under T1 Separation Axiom
• A computation of the ninth Dedekind Number
• MECA: A Mechanism-Centered Agent for Constructing Well-Specified and Valuable Mathematical Conjectures
• IntSeqBERT: Learning Arithmetic Structure in OEIS via Modulo-Spectrum Embeddings
• LeanConjecturer: Automatic Generation of Mathematical Conjectures for Theorem Proving
• Learning Formal Mathematics From Intrinsic Motivation
• Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero
• HyGRAIL: Cost-Aware and Evidence-Grounded Scientific Hypothesis Discovery over Knowledge Graphs

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering