arXiv (All)
open access
Sequential Sampling for Binary Classification: Two LLMs are (Almost) All You Need
We study how to orchestrate multiple large language models (LLMs) for reliable binary classification when models differ in accuracy, monetary cost, and response time. A decision-maker adaptively chooses which LLM to query, updates its belief after each response, and stops once sufficient confidence
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
- Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation#984165
- Persuading large language models to comply with objectionable requests.#235981
- NetLLM: Adapting Large Language Models for Networking#328716
- Large Language Bayes Is Not Reparameterisation-Invariant#1154888
- Flip, Don't Shuffle: Watermarking LLMs at the Speed of Inference#926723
Record · ID 1117357
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