LLM reasoning / chain-of-thought

pruning-based CoT refinement

Superseded baseline#555 of 772 most-superseded

Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here

1 papers critique it · 0 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites pruning-based CoT refinement as a baseline.

merely pruning redundant or erroneous steps does not ensure accurate knowledge usage in the core thought
CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.