Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Compute
Aman Sharma, Paras Chopra
We revisit test-time scaling for language model reasoning and ask a fundamental question: at equal token budget and compute, is it better to run multiple independent chains in para…
cs.LG2025
Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM Reasoning
Aman Sharma, Paras Chopra
We introduce a simple, yet novel entropy-based framework to drive token efficiency in large language models during reasoning tasks. Our approach uses Shannon entropy from token-lev…