The paper introduces a probabilistic‑circuit framework for fusing opinions from multiple black‑box experts in noisy, conflict‑prone environments. It dynamically assigns context‑specific credibility to each expert, allowing reliable aggregation without needing access to their internal models or retraining. Experiments on multiple‑choice question answering with large language models show that this method outperforms individual models and static ensemble baselines, consistently improving predictive accuracy and decision reliability under disagreement.
arXiv:2607. 20529v1 Announce Type: cross Abstract: Large Language Model (LLM) ensembles are increasingly used to improve reliability by combining predictions from multiple LLMs.
The paper addresses the lack of system‑level confidence estimates in multiagent language model systems such as collaborative reasoning and debate. It introduces confidence composition methods, including confidence‑aware routing and log‑odds pooling, to combine agent confidences while maintaining selective utility and probabilistic reliability. Experiments on five benchmarks with diverse model pairs show that gated‑fusion techniques improve AUARC and Brier scores compared to single‑agent and standard debate baselines, and a shared dependence discount further enhances reliability.
arXiv:2609.39645v1 Announce Type: cross Abstract: Multi-agent collaboration lets large language models (LLMs) improve question answering through deliberation and feedback. Yet shared discussion coupl...
arXiv:2604. 17289v2 Announce Type: replace Abstract: Supervised fine-tuning of large language models relies on human-annotated data, yet annotation pipelines routinely involve multiple crowdworkers of heterogeneous expertise.
The paper introduces Bayesian Dialectical Argumentation (BDA), a method for aggregating answers from multiple large language models (LLMs) in a council setting. BDA treats each LLM’s typed moves—proposals, challenges, and concessions—as evidence in a classical annotator model, estimating per-agent reliability even when some agents are persistently unreliable. By weighting evidence according to these inferred reliabilities, BDA produces calibrated posterior probabilities for candidate answers and can invert unreliable agents instead of merely outvoting them, achieving superior calibration and robustness on both binary and multi-class benchmarks without extra LLM calls.
arXiv:2605. 15416v2 Announce Type: replace-cross Abstract: Jung et al.
arXiv:2606. 20245v1 Announce Type: new Abstract: Large language models (LLMs) have achieved strong performance across a wide range of language-based tasks by leveraging both extensive parametric knowledge and in-context learning ability, enabling them to incorporate external information provided in the input prompt.
arXiv:2606. 13591v1 Announce Type: new Abstract: Confidence is used for reliability, oversight, and a range of downstream decision tasks in Natural Language Processing (NLP), yet no existing method produces or evaluates a confidence for the output of a multiagent system.
The paper introduces multi-expert Conformal Risk Control (CRC) algorithms for pairwise LLM-as-a-Judge evaluation in open-ended dialogue. Two initial methods—Score Averaging and Decision Voting—aggregate at the score and decision levels, respectively, and outperform single-expert approaches on homogeneous expert panels. To address limited coverage on heterogeneous panels, the authors propose Marginal‑Calibrated Conformal Consensus (MC3), which captures distinct per‑expert scoring scales through threshold ratios while maintaining a unified decision function, and demonstrate its effectiveness on a new 1,800‑pair human pairwise‑preference benchmark called Panel.
The paper introduces Bayesian backward reasoning as a label‑free anchor for multi‑agent collective decision‑making. By constructing reverse posteriors from explicit likelihoods, the authors obtain differently factorized approximations of the underlying posterior, reducing shared errors among agents. Using Jensen‑Shannon divergence to rank agents, they propose three aggregation strategies—hard selection (MinJS), soft reweighting (FwdJS), and log‑linear fusion (LogLin)—which consistently outperform baseline methods on the DDXPlus benchmark across five LLM backbones, especially when agents disagree.
DirEAG introduces a Dirichlet Evidence Aggregation technique to calibrate verbalized confidence in large language models performing mathematical reasoning. By converting each elicited answer-confidence pair into calibrated soft evidence over candidate answers and a null state, it addresses prompt- and task-dependent bias that simple averaging or heuristic aggregation cannot handle. Experiments on GSM8K, SVAMP, and GSM-Hard with Qwen, Mistral, and Gemma models demonstrate that DirEAG achieves better calibration while maintaining competitive answer selection compared to existing methods.
arXiv:2606. 19950v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) show great potential in medical tasks, but their elicited confidence often misaligns with actual accuracy, potentially leading to misdiagnosis or overlooking correct advice.