Learning to Learn from Context: Synthetic Training from Perturbed Public Documents

arXiv:2609.33642 · cs.CL, cs.AI · Submitted 2026-09-27 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-27

Updated: 2026-09-27

Code: https://github.com/Tencent-Hunyuan/CL-bench

Terminology

• Trace — 30× in this paper · explained in 2 episodes
• Benchmark — 28× in this paper · explained in 2 episodes
• Accuracy — 15× in this paper · explained in 1 episode
• Reasoning Traces — 11× in this paper · explained in 3 episodes
• Reward Function — 7× in this paper · explained in 2 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Reinforcement Learning — 5× in this paper · explained in 4 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Provenance — 4× in this paper · explained in 4 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Hallucination — 3× in this paper · explained in 3 episodes
• Archetype — 2× in this paper · explained in 1 episode
• Generative AI — 2× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Synthetic Data Generation — 2× in this paper · explained in 5 episodes
• Agentic Coding — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Reward Hacking — 1× in this paper · explained in 8 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• gpt-oss-120b & gpt-oss-20b Model Card
• Kimi K3: Open Frontier Intelligence
• ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems
• On the Measure of Intelligence
• Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs
• CL-bench Life: Can Language Models Learn from Real-Life Context?
• CL-bench: A Benchmark for Context Learning
• Gemma 4 Technical Report
• The Pile: An 800GB Dataset of Diverse Text for Language Modeling
• Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models
• Humanity's Last Exam
• Modular Techniques for Synthetic Long-Context Data Generation in Language Model Training and Evaluation
• Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries
• OJBench: A Competition Level Code Benchmark For Large Language Models
• Measuring short-form factuality in large language models
• GLM-5: from Vibe Coding to Agentic Engineering
• LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models
• Group Sequence Policy Optimization
• Instruction-Following Evaluation for 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