efficiency-training

Tag

Cards List
#efficiency-training

Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability

Hugging Face Daily Papers ↗ · 2026-10-02 Cached

This paper investigates whether training LLMs for shorter, more efficient chain-of-thought reasoning harms the faithfulness and monitorability of that reasoning. It finds faithfulness generally declines due to reduced model consistency, while monitorability remains relatively robust even with much shorter CoT outputs.

0 favorites 0 likes
← Back to home

Submit Feedback