GIST: Gibbs-Targeted Hierarchical Data Selection for Offline RLVR
cs.AI, cs.LG
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/EleutherAI/lm-evaluation-harness
Terminology
Sources
- Program Synthesis with Large Language Models
- Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning
- The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment
- MiniLLM: On-Policy Distillation of Large Language Models
- Reinforced Self-Training (ReST) for Language Modeling
- Reinforcement Learning with Deep Energy-Based Policies
- Measuring Mathematical Problem Solving With the MATH Dataset
- The Curious Case of Neural Text Degeneration
- RL with KL penalties is better viewed as Bayesian inference
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- Unified Data Selection for LLM Reasoning
- LIMR: Less is More for RL Scaling
- Rho-1: Not All Tokens Are What You Need
- Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability
- Understanding R1-Zero-Like Training: A Critical Perspective
- Which Tokens Matter? Adaptive Token Selection for RLVR with the Relative Surprisal Index
- Coresets for Data-efficient Training of Machine Learning Models
- Training language models to follow instructions with human feedback
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