Masking loss on early training tokens and injecting embeddings from an auxiliary reader improves LLM accuracy on several reasoning benchmarks.
Cepo: Empowering llama with reasoning using test-time compute
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
-
Read Quietly, Think Aloud: Decoupling Comprehension and Reasoning in LLMs
Masking loss on early training tokens and injecting embeddings from an auxiliary reader improves LLM accuracy on several reasoning benchmarks.