arXiv:2608.30373v1 Announce Type: new Abstract: Multi-Agent Debate (MAD) has been widely adopted to improve LLM-based evaluation by prompting multiple agents to negotiate and reach a consensus. Howev...
arXiv:2605. 12530v2 Announce Type: replace-cross Abstract: LLM fairness should be evaluated through in-situ behavioral pattern rather than standardized-test Q&A benchmarks.
Multi-Agent Debate (MAD) has been widely adopted to improve LLM-based evaluation by prompting multiple agents to negotiate and reach a consensus. However, for subjective rubric-based scoring, inter-ag...
arXiv:2608. 07762v1 Announce Type: new Abstract: LLM benchmarks can build an organization's reputation and attract customers, but only when results are transparent and verifiable.
GAUGE is a new offline protocol that evaluates whether the common practice of using an LLM-as-a-judge to rank task‑oriented agents actually aligns with a verifiable reward. Across 25 agents from six providers on two benchmarks, GAUGE finds that user satisfaction scores are largely uncorrelated with task success, and that the judge’s ranking loses precision when agents are closely matched in performance. The study highlights a gap between ranking validity and construct validity in current evaluation practices.
The study introduces PV‑SST, a peer‑voted social‑platform testbed, and conducts a preregistered matched‑exposure experiment across four topics, four seeds, four model families, and three larger variants, totaling 448 trials. Results show that feeding agents a ranked list of prior peer posts increases lexical similarity in both the core panel and larger variants, but does not produce a reliable advantage in opinion alignment or survival rates. The only robust finding is lexical convergence driven by the peer‑ranked feed, with no consistent coordination benefit across models or topics.
arXiv:2610.35930v1 Announce Type: cross Abstract: Multi-agent debate (MAD) aims to improve language-model decisions through the exchange of arguments, yet agreement after debate need not reflect inde...
The paper introduces a method to reduce sycophancy in large language models by using the Bayesian Truth Serum (BTS) as a reward signal in Group Relative Policy Optimization (GRPO). BTS rewards answers that are surprisingly common among a model’s own outputs, eliminating the need for labeled data or preference annotations. Experiments on a true/false benchmark show a significant drop in answer‑flip rates under user pressure and an increase in accuracy, outperforming other reward schemes such as SMART.
arXiv:2609.23264v1 Announce Type: new Abstract: Peer-review evaluation is increasingly being automated with LLM-as-a-judge metrics, but this creates a measurement risk. A review may receive a high sc...
arXiv:2606. 21008v2 Announce Type: replace-cross Abstract: The metanym game is a competitive word game for LLMs that measures structural intelligence against established cognitive-science constructs.
arXiv:2609.23201v1 Announce Type: new Abstract: Benchmark scores increasingly influence the development, marketing, and selection of large language models (LLMs). Yet an overall score is interpretabl...
arXiv:2609.13824v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to evaluate the responses of other language models. This approach, known as LLM-as-a-Judge, is faste...