The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models
cs.AI, cs.CL
Submitted: 2026-05-07
Updated: 2026-11-16
Code: https://github.com/qinchonghanzuibang/Granularity-Axis
Terminology
Sources
- The Llama 3 Herd of Models
- Qwen3 Technical Report
- From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents
- Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithms
- Epidemic Modeling with Generative Agents
- Whose Opinions Do Language Models Reflect?
- Large Language Models Show Human-like Social Desirability Biases in Survey Responses
- Character-LLM: A Trainable Agent for Role-Playing
- In-Context Impersonation Reveals Large Language Models' Strengths and Biases
- Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs
- Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models
- Personas as a Way to Model Truthfulness in Language Models
- The Geometry of Categorical and Hierarchical Concepts in Large Language Models
- Toy Models of Superposition
- Sparse Autoencoders Find Highly Interpretable Features in Language Models
- Scaling and evaluating sparse autoencoders
- Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
- Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders
- The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models
- Steering Language Models With Activation Engineering
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents