FPSRG: Heterogeneous User Simulation First-Person Post-Training and Multidimensional Semantic Response Grids
cs.AI
Submitted: 2026-11-12
Updated: 2026-11-12
Terminology
Sources
- Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering
- Plug and Play Language Models: A Simple Approach to Controlled Text Generation
- ORBIT: Training-Free Multi-Attribute Behavioral Steering via Orthogonal Subspace Rotation
- LoRA: Low-Rank Adaptation of Large Language Models
- LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
- Persona Dosing: Calibrated Activation Steering for Graded Trait Control
- The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models
- Illuminating search spaces by mapping elites
- Generative Agents: Interactive Simulacra of Human Behavior
- AI Simulations Grounded in Rich Self-Reports Increase Accuracy and Reduce Distortion
- Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting
- ActTraitBench: Quantifying the Knowledge-Decision Gap in Large Language Models via Human-Grounded Behavioral Validation
- Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing
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