Sparse Reward Subsystem in Large Language Models
cs.CL
Submitted: 2026-02-01
Updated: 2026-11-04
Terminology
Sources
- Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- Language Model Circuits Are Sparse in the Neuron Basis
- Program Synthesis with Large Language Models
- Qwen Technical Report
- States Hidden in Hidden States: Implicit Discrete State Representations Emerge in LLMs' Hidden States
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- A polar coordinate system represents syntax in large language models
- Toy Models of Superposition
- H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs
- The Llama 3 Herd of Models
- Textbooks Are All You Need
- Neural Probe-Based Hallucination Detection for Large Language Models
- Let's Verify Step by Step
- House of Cards: Massive Weights in LLMs
- OpenAI GPT-5 System Card
- LLaMA: Open and Efficient Foundation Language Models
- Qwen3 Technical Report
- SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild
- Interpretable Reward Model via Sparse Autoencoder
- Learning to Reason without External Rewards
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data