CascadeLedger: Counterfactual Auditing of Information and Resource Integrity in LLM Cascades

arXiv:2610.20668 · cs.CR, cs.CL, cs.LG · Submitted 2026-10-14 · Read on arXiv

cs.CR, cs.CL, cs.LG

Submitted: 2026-10-14

Updated: 2026-10-16

Comments: 38 pages, 6 figures

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Trace — 4× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
• Training Verifiers to Solve Math Word Problems
• DeepSeek-V3 Technical Report
• Cascadia: An Efficient Cascade Serving System for Large Language Models
• RewardBench: Evaluating Reward Models for Language Modeling
• CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoning
• ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities
• Cluster, Route, Escalate: Cascaded Framework for Cost-Aware LLM Serving
• Adaptive LLM Routing under Budget Constraints
• Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
• Cheap Verifiers, Large Blind Spots: Measuring the Reliability Cost of Cost-Saving Cascades
• Toolformer: Language Models Can Teach Themselves to Use Tools
• Using Common Random Numbers for Simulation-based Planning with Rollouts
• $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Estimating the Social Cost of Corporate Data Breaches
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills