RLVR training for language models exhibits an unlearnability phenomenon where certain hard examples stay unlearnable due to low gradient similarity and ungeneralizable reasoning patterns.
Output format: Return ONLY a valid JSON array with no additional text, markdown code fences, or explanations before or after
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Unlearnability Phenomenon in RLVR for Language Models
RLVR training for language models exhibits an unlearnability phenomenon where certain hard examples stay unlearnable due to low gradient similarity and ungeneralizable reasoning patterns.