The Knowledge Layer Model (KLM): Evidence-Visible AI Output, Routing Diagnostics, and Negative Results
cs.AI, cs.CL
Submitted: 2026-10-30
Updated: 2026-10-30
Comments: 47 pages, 1 figure, 14 tables. Includes Appendix A
Code: https://github.com/omasim/KLM
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Non-Determinism of "Deterministic" LLM Settings
- Attention is not Explanation
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- AttributionBench: How Hard is Automatic Attribution Evaluation?
- Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents
- CiteME: Can Language Models Accurately Cite Scientific Claims?
- From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents
- CiteEval: Principle-Driven Citation Evaluation for Source Attribution
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