AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

The Lattice Representation Hypothesis and Concept Algebra in LLMs

Bo Xiong

ICLR 2026 · Large language models › Language, safety and interpretability · approach: Linguistic encoding in LLM representations

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
estimate attribute directions with regularized LDA instead of class-mean difference or random (ablation)LLM embeddings (LLaMA3.1-8B, Gemma-7B, Mistral-7B) · WordNet domains formal context recoveryF1: Gemma WN-Animal 50.1 (Mean) -> 83.2Improved
use projection-based soft inclusion with LDA directions for subsumption (ablation)LLM embeddings · WordNet partial order inferenceF1: LLaMA WN-Animal 66.7 (Mean) -> 77.1Improved
use lattice concept algebra (meet/join) instead of mean-embedding similarity (ablation)LLM embeddings · WordNet meet/join rankingMRRImproved
move from physical to abstract domainslattice geometry · WordNet Event and Cognition vs Animal/Plant/FoodF1: LLaMA formal context F1 82.5 (Animal) -> 71.5 (Event)Hurt
scale LLaMA-3 from 3B to 70B (ablation)lattice geometry · WordNet domainsMacro-F1Improved
Linear versus Mean on Mistral WN-Plant partial order (ablation)soft inclusion · WN-Plant partial orderF1: Mean 60.5 vs Linear 57.1 (Mistral)Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy