arXiv (All)
open access
From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing
Existing LLM routing methods often construct supervision from a single sampled response for each query--model pair. Because LLM generation is stochastic, however, such an observation can be an unstable estimate of model capability: semantically equivalent query formulations and repeated decoding may
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing#1141685
- The Routing Plateau: Understanding the Accuracy Limits of LLM Routers#1118597
- FlexRouter: Learning Complementary Model Sets for Flexible LLM Routing#1143186
- Which Model Is Actually Serving You? IRIS: Budgeted Black-Box Auditing of Model Substitution and Routing Dilution in LLM Gateways#394317
- Towards Mitigating Excessive Forgetting in LLM Unlearning via Entanglement-Guidance with Proxy Constraint#1052017
Record · ID 927339
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive