LLM reasoning / chain-of-thought

parameter merging frameworks

Superseded baseline#511 of 772 most-superseded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 parameter merging frameworks as a baseline.

most existing merging frameworks typically assume a degree of orthogonality in parameter space and do not address the logical conflicts that arise when multiple teachers provide divergent reasoning paths for the same problem.
"The Whole Is Greater Than the Sum of Its Parts": A Compatibility-Aware Multi-Teacher CoT Distillation Framework

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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.