Retrievable Gradients: Continual Post-Training Without Cumulative Weight Drift

arXiv:2606.15734 · cs.CL, cs.AI, cs.IR, cs.LG · Submitted 2026-06-14 · Read on arXiv

cs.CL, cs.AI, cs.IR, cs.LG

Submitted: 2026-06-14

Updated: 2026-10-11

Code: https://github.com/oneal2000/ReGrad

Terminology

• Adaptation — 2× in this paper · explained in 1 episode
• Catastrophic Forgetting — 1× in this paper · explained in 5 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Meta-learning — 1× in this paper · explained in 2 episodes
• RAG — 1× in this paper · explained in 3 episodes

Sources

• From Local to Global: A Graph RAG Approach to Query-Focused Summarization
• Scaling Laws For Dense Retrieval
• The Pile: An 800GB Dataset of Diverse Text for Language Modeling
• Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps
• Towards Continual Knowledge Learning of Language Models
• Active Retrieval Augmented Generation
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• Balancing Continuous Pre-Training and Instruction Fine-Tuning: Optimizing Instruction-Following in LLMs
• Dense Passage Retrieval for Open-Domain Question Answering
• Mass-Editing Memory in a Transformer
• Fast Model Editing at Scale
• In-Context Retrieval-Augmented Language Models
• S-LoRA: Serving Thousands of Concurrent LoRA Adapters
• Caseformer: Pre-training for Legal Case Retrieval Based on Inter-Case Distinctions
• Enhancing Judgment Document Generation via Agentic Legal Information Collection and Rubric-Guided Optimization
• STARD: A Chinese Statute Retrieval Dataset with Real Queries Issued by Non-professionals
• Skill Retrieval Augmentation for Agentic AI
• Towards Unification of Hallucination Detection and Fact Verification for Large Language Models
• DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models
• Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering