River-LLM enables seamless token-level early exit in decoder-only LLMs via a KV-shared river mechanism and similarity-based error prediction, delivering 1.71-2.16x practical speedup on reasoning tasks while preserving generation quality.
Advances in Neural Information Processing Systems , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2representative citing papers
DoLa reduces hallucinations in LLMs by contrasting logits from later versus earlier layers during decoding, improving truthfulness on TruthfulQA by 12-17 absolute points without fine-tuning or retrieval.
citing papers explorer
-
River-LLM: Large Language Model Seamless Exit Based on KV Share
River-LLM enables seamless token-level early exit in decoder-only LLMs via a KV-shared river mechanism and similarity-based error prediction, delivering 1.71-2.16x practical speedup on reasoning tasks while preserving generation quality.
-
DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
DoLa reduces hallucinations in LLMs by contrasting logits from later versus earlier layers during decoding, improving truthfulness on TruthfulQA by 12-17 absolute points without fine-tuning or retrieval.