Line of inquiry
Inquiring lines›How can we train models to be prop…›What architectural and training in…›this line of inquiry
When and why does majority voting improve reasoning quality at test time?
A broader line of inquiry — a family of 45 specific questions the research asks around this. Follow one into its inquiring-line page, or move sideways to a related line below.
Questions in this line of inquiry 45
Specific inquiring lines the field asks around this — ordered from the most general framing down to the most specific angle.
- Why does majority voting reward work better than other test-time aggregation methods?
- When does multi-agent voting help versus hurt performance on tasks?
- How does majority voting fail when reasoning samples lack genuine diversity?
- Does majority voting reliably signal correctness without risking reward hacking?
- Can test-time voting improve reasoning beyond the base model's original capabilities?
- What happens when majority voting converges to a single answer?
- Can voting work at every level of task decomposition, not just whole problems?
- How does training-time voting differ from inference-time majority voting over samples?
- Does majority voting prevent confident but incorrect answers from being reinforced?
- What makes consensus games work without retraining the base model?
- How do correlated errors across agents threaten voting-based error correction systems?
- What intermediate information does majority voting discard from reasoning chains?
- What compute costs does majority-vote consensus sampling add versus supervised training?
- What determines whether minority signals succeed in changing a group's consensus position?
- How does training-time consensus differ from inference-time majority voting over samples?
- What mechanisms let generative models escape collapse through majority voting?
- Can a policy game vote-based rewards through distinguishability unrelated to quality?
- Can crowdsourced voting reliably identify correct answers on graduate-level factual questions?
- Can aggregation cancel out independent errors but not shared training-data biases?
- Can calibrated confidence reduce misleading consensus in group deliberation?
- How does majority vote consensus handle cases where the consensus is confidently wrong?
- How do ensemble methods reduce bias in automated evaluation?
- Can social choice theory mathematically represent stakeholder preferences in AI?
- Why do self-consistency methods fail where pretraining bias is strongest?
- Why does consensus-seeking destroy information in normative but not factual tasks?
- Why might expanding group deliberation beyond five people produce bland consensus statements?
- Why does low temperature sampling extract consensus from diverse training data?
- Why does validator consensus solve agreement but not answer correctness?
- Why do some prompts benefit from aggregation while others do not?
- Does increasing quorum threshold fix agreement without semantic correctness?
- What signals detect when consensus training is silently degrading performance?
- How do social correctives prevent premature consensus in human debate?
- What role does consensus merging play in dynamic task decomposition?
- Can citizen assemblies and value pluralism replace single utility optimization?
- Can additive welfare aggregation justify removing minority override rights?
- What information is lost when majority labels discard minority interpretations?
- When do aggregated imperfect demonstrations fail to outperform the best expert?
- Why do initially correct group members move away from right answers during deliberation?
- What does egalitarian social choice theory contribute to AI alignment?
- How can developers balance multiple conflicting fairness goals simultaneously?
- Which prompt properties determine whether variance helps under majority voting?
- How often do survey respondents under-report socially undesirable voting behaviors?
- How might aggregative welfare goals justify overriding minority preferences?
- How do citizen assembly preferences reduce LLM political bias?
- What constant multiplier scales the veto-holder ratio into absolute welfare cost?