On CoTemp QA, supervised fine-tuning with raw R1 traces gave the best model accuracy while human raters found those traces least interpretable, showing model-useful traces and human-readable traces can diverge.
Guidelines: • The answer NA means that the paper does not include experiments
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Do Cognitively Interpretable Reasoning Traces Improve LLM Performance?
On CoTemp QA, supervised fine-tuning with raw R1 traces gave the best model accuracy while human raters found those traces least interpretable, showing model-useful traces and human-readable traces can diverge.