arXiv (All)
open access
Beyond Truncation: Rethinking LLM Decoding as Ensemble Pruning
We introduce Mahalanobis-Ensemble Decoding (ME-Decoding), a novel Large Language Model (LLM) decoding framework that frames candidate token selection as ensemble pruning. Existing selection strategies rely predominantly on scalar probabilities, ignoring geometric semantic relationships and causing c
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
- Beyond Truncation: Rethinking LLM Decoding as Ensemble Pruning#965422
- Pair-In, Pair-Out: Latent Multi-Token Prediction for Efficient LLMs#229535
- Unifying Conformal Language Tasks with In-Context Ensembles#925378
- Unifying Conformal Language Tasks with In-Context Ensembles#921142
- FLaG: Frequency-Domain Latent-attention Gated Pooling for Token Aggregation#820836
Record · ID 1012890
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