EffComp: Efficient Prompt Compression via Hybrid Reinforcement & Supervised Learning
cs.CL
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- Large Language Models Hallucination: A Comprehensive Survey
- MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
- Unsupervised Cross-lingual Representation Learning at Scale
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents
- Mistral 7B
- TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
- Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation
- SuperRL: Reinforcement Learning with Supervision to Boost Language Model Reasoning
- mmBERT: A Modern Multilingual Encoder with Annealed Language Learning
- Training language models to follow instructions with human feedback
- Proximal Policy Optimization Algorithms
- TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Gemma 2: Improving Open Language Models at a Practical Size
- Contextual Compression in Retrieval-Augmented Generation for Large Language Models: A Survey
- Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
- C-Pack: Packed Resources For General Chinese Embeddings
- Qwen2 Technical Report
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