The paper introduces a pluralistic agreement index, Gamma, to quantify how often wrong runs of large language models (LLMs) agree with the majority consensus. By decomposing Gamma into a mechanical component and a preference‑unexplained residual, the authors show that on GPT‑4.1 the mechanical part explains most of the agreement on multiple‑choice benchmarks but only about half on open‑domain tasks, revealing a residual bias that can cause self‑consistency to backfire on hard questions. The study provides a quantitative framework for understanding when majority voting over LLM samples improves or harms accuracy, without proposing new voting methods.
arXiv:2608. 11403v1 Announce Type: new Abstract: Self-consistency (SC) via majority vote is a widely used way to spend inference-time compute: sample N chains of thought, return the plurality answer.
arXiv:2606. 13685v1 Announce Type: cross Abstract: LLM-as-a-Judge is now widely used to rank model outputs, train reward models, and populate public leaderboards, but its run-to-run reliability remains under-characterized.
arXiv:2607. 08065v1 Announce Type: new Abstract: LLM-as-judge (Zheng et al.
arXiv:2606. 16617v1 Announce Type: cross Abstract: Sycophancy in LLMs is documented across 70+ papers, but expert agreement on construct boundaries remains low (ICC=.
arXiv:2607. 23976v1 Announce Type: cross Abstract: Appending a two-word confirmation tag to a decision question -- "Is X the better choice?
arXiv:2607. 10139v1 Announce Type: cross Abstract: Selecting the correct answer from a pool of candidate reasoning chains is the engine of test-time scaling, yet the standard selectors each carry a cost: self-consistency inherits the errors of the single model it resamples, and trained reward models need labeled data and transfer poorly off-distribution.
arXiv:2608. 15980v1 Announce Type: cross Abstract: Preference benchmarks are built by hiring annotators, and the identity of those annotators is treated as an implementation detail.
arXiv:2607. 25136v1 Announce Type: new Abstract: Research on preference optimization often varies the training objective while holding the data fixed.
arXiv:2608. 07813v1 Announce Type: new Abstract: An LLM judge deployed inside a reasoning pipeline does not merely measure quality, it decides which answer ships.
Appending a two-word confirmation tag to a decision question -- "Is X the better choice? " versus "X is the better choice, right?
The paper investigates how the order of candidate documents in a prompt affects the decisions made by large‑language‑model (LLM) scorers, even when their ranking quality is similar. It shows that five scorers with only a 0.010 nDCG@10 difference can produce retained‑set overlaps as low as 0.66–0.84, and that existing rerankers still exhibit significant order dependence. The authors propose Order‑Consistency SFT (OC‑SFT), a training method that reduces this dependence, maintaining ranking quality while improving decision stability across multiple tasks.
arXiv:2607. 10202v1 Announce Type: new Abstract: Cross-model comparisons read divergence in value dispositions as evidence that language models hold individuated values.