When Self-Consistency Backfires: Majority Vote Hurts the Majority of Hard Science Problems for Small LLMs.

arXiv:2608.11403v3 Announce Type: replace Abstract: Majority-vote self-consistency (SC) lowers per-problem accuracy on most GPQA Diamond problems for small instruction-tuned models: on 56.6% of problems for Qwen2.5-7B and 65.7% for Llama-3-8B. An obvious fix i