AI/ ai · llm-evaluation · self-consistency · small-models

Majority Voting Makes Small AI Models Worse at Hard Science

A new study finds that self-consistency voting lowers accuracy on most hard GPQA problems for small LLMs, and simple confidence fixes don't help either.

Asking a small AI model the same hard science question 64 times and picking the most common answer often makes it wrong more often, not less.

A new arXiv paper tested self-consistency - the common trick of sampling multiple answers and taking a majority vote - on GPQA Diamond, a benchmark of hard science questions. For Qwen2.5-7B, majority voting hurt accuracy on 56.6% of the problems it was tested on; for Llama-3-8B, it hurt 65.7%. The researchers then tried the obvious fix: a confidence gate that skips voting when the model's token-level uncertainty looks low. That gate failed too, because the entropy measurement tracks how verbose or hedgy the model's writing is, not how sure it actually is about the answer - on Qwen2.5-7B-Instruct-Turbo, samples that contradicted their own problem's majority answer still looked confident most of the time, with 75.7% scoring above a 10-nat confidence threshold, a finding that held up when re-tested on a separate, pre-registered set of 69 problems.

That matters for anyone building a system that routes between a cheap single answer and an expensive multi-sample vote based on a confidence score. The signal discriminates fine across different questions but is close to useless for the within-question call a router actually needs to make, and a second natural fix - checking whether the top two answers agree - also failed, with no explanation the authors could pin down. It's a useful check on the assumption that tricks proven on huge frontier models transfer cleanly down to the 7B-8B models many teams actually run.

The paper's honesty extends to its own limits: a planned replication on a second model couldn't be evaluated, and three reasoning-focused open models each failed to evaluate on hosted serverless inference at a small budget, for three separate reasons the paper details - all three are downloadable, so the bottleneck was the metered API, not the models themselves.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →